mega_venik/sdcv
1
0
Fork 0
mirror of https://github.com/Dushistov/sdcv.git synced 2025-12-15 17:31:56 +00:00
Code Issues Projects Releases Wiki Activity

Compare commits

base: mega_venik:v0.5.4
Branches Tags
mega_venik:master mega_venik:fix-include mega_venik:gh-pages mega_venik:sdcv_on_rust
mega_venik:v0.5.5 mega_venik:v0.5.4 mega_venik:v0.5.3 mega_venik:v0.5.2 mega_venik:v0.5.1
..
compare: mega_venik:sdcv_on_rust
Branches Tags
mega_venik:master mega_venik:fix-include mega_venik:gh-pages mega_venik:sdcv_on_rust
mega_venik:v0.5.5 mega_venik:v0.5.4 mega_venik:v0.5.3 mega_venik:v0.5.2 mega_venik:v0.5.1

3 Commits
v0.5.4 ... sdcv_on_ru

Author SHA1 Message Date
Evgeniy A. Dushistov
21a0678cba implement support of gziped index files 2016-08-06 00:31:37 +03:00
Evgeniy A. Dushistov
3aaae57139 add cargo lock 2016-07-03 19:43:43 +03:00
Evgeniy A. Dushistov
5b26d06493 something working 2016-07-03 16:56:30 +03:00
76 changed files with 7064516 additions and 4054 deletions
Expand all files Collapse all files

2
.clang-format
View File

@@ -15,7 +15,7 @@ BreakBeforeBinaryOperators: true
BreakBeforeTernaryOperators: true
BreakConstructorInitializersBeforeComma: true
BinPackParameters: true
ColumnLimit: 120
ColumnLimit: 0
ConstructorInitializerAllOnOneLineOrOnePerLine: false
DerivePointerAlignment: false
ExperimentalAutoDetectBinPacking: false

48
.github/workflows/main.yml vendored
View File

@@ -1,48 +0,0 @@
name: CI
on:
push:
branches:
- master
pull_request:
branches:
- master
schedule:
- cron: '00 02 */4 * *'
env:
RUST_BACKTRACE: 1
jobs:
tests:
name: Run tests
runs-on: ${{ matrix.os }}
strategy:
fail-fast: true
matrix:
os: [ubuntu-latest]
steps:
- uses: actions/checkout@v2
with:
submodules: 'recursive'
- uses: jwlawson/actions-setup-cmake@v1.4
with:
cmake-version: '3.5.1'
github-api-token: ${{ secrets.GITHUB_TOKEN }}
- name: Check versions
run: |
set -e
cmake --version
gcc --version
echo "end of versions checking"
shell: bash
- name: Run tests
run: |
set -e
cd $GITHUB_WORKSPACE
mkdir build
cd build
cmake -DBUILD_TESTS=True ..
make -k -j2 VERBOSE=1
ctest --output-on-failure
shell: bash

48
.travis.yml Normal file
View File

@@ -0,0 +1,48 @@
#
# Available repositories are listed here:
# https://github.com/travis-ci/apt-source-whitelist/blob/master/ubuntu.json
#
sudo: false
language: cpp
matrix:
include:
- env: COMPILER_VERSION=4.8
os: linux
compiler: g++
addons:
apt:
sources:
- ubuntu-toolchain-r-test
- kalakris-cmake
- ubuntu-sdk-team
packages:
- g++-4.8
- cmake
- libglib2.0-dev
# - env: COMPILER_VERSION=3.5
# os: linux
# compiler: clang++
# addons:
# apt:
# sources:
# - ubuntu-toolchain-r-test
# - llvm-toolchain-precise-3.5
# packages:
# - clang-3.5
# - cmake
# - libglib2.0-dev
before_script:
- mkdir build
- cd build
- CC=$CC-${COMPILER_VERSION} CXX=$CXX-${COMPILER_VERSION} cmake -DBUILD_TESTS=True ..
- cd ..
script:
- cd build
- make -k -j2 VERBOSE=1
- ctest --output-on-failure

42
CMakeLists.txt
View File

@@ -1,18 +1,24 @@
project(sdcv)
cmake_minimum_required(VERSION 3.5 FATAL_ERROR)
cmake_policy(VERSION 3.5)
# Older versions have a different signature for CMAKE_MINIMUM_REQUIRED,
# check it manually just to make sure
if (${CMAKE_MAJOR_VERSION}.${CMAKE_MINOR_VERSION} LESS 2.8)
message(FATAL_ERROR "${PROJECT_NAME} requires at least CMake v2.8."
" You are running v${CMAKE_MAJOR_VERSION}.${CMAKE_MINOR_VERSION}."
" Please upgrade." )
endif(${CMAKE_MAJOR_VERSION}.${CMAKE_MINOR_VERSION} LESS 2.8)
set(CMAKE_CXX_STANDARD 11)
set(CMAKE_CXX_STANDARD_REQUIRED True)
set(CMAKE_CXX_EXTENSIONS False)
# If we get this far, use the modern signature. This will also cause newer
# CMake versions to try to be backwards-compatible with the desired version
cmake_minimum_required(VERSION 2.8 FATAL_ERROR)
cmake_policy(VERSION 2.8)
include("${CMAKE_CURRENT_SOURCE_DIR}/cmake/compiler.cmake")
set(ZLIB_FIND_REQUIRED True)
include(FindZLIB)
set(GLIB2_REQ "'glib-2.0 >= 2.36'")
set(GLIB2_REQ "'glib-2.0 >= 2.6.1'")
set(CMAKE_MODULE_PATH "${CMAKE_SOURCE_DIR}/cmake")
include("${CMAKE_CURRENT_SOURCE_DIR}/cmake/FindGLIB2.cmake")
@@ -21,15 +27,11 @@ if (NOT GLIB2_FOUND)
"make sure that you install it")
endif()
set(WITH_READLINE True CACHE BOOL "Use readline library")
if (WITH_READLINE)
find_path(READLINE_INCLUDE_DIR readline/readline.h)
find_library(READLINE_LIBRARY NAMES readline)
if (NOT (READLINE_INCLUDE_DIR AND READLINE_LIBRARY))
set(WITH_READLINE False CACHE FORCE)
endif ()
endif (WITH_READLINE)
find_path(READLINE_INCLUDE_DIR readline/readline.h)
find_library(READLINE_LIBRARY NAMES readline)
if (READLINE_INCLUDE_DIR AND READLINE_LIBRARY)
set(WITH_READLINE True)
endif ()
option(ENABLE_NLS "Enable NLS support" True)
@@ -82,7 +84,6 @@ configure_file(${CMAKE_CURRENT_SOURCE_DIR}/config.h.cmake
include_directories(
${ZLIB_INCLUDE_DIR}
${GLIB2_INCLUDE_DIRS}
${READLINE_INCLUDE_DIR}
${CMAKE_CURRENT_SOURCE_DIR}/src/lib
${CMAKE_CURRENT_BINARY_DIR}
)
@@ -95,7 +96,7 @@ set(CPACK_PACKAGE_VENDOR "Evgeniy Dushistov <dushistov@mail.ru>")
set(CPACK_PACKAGE_DESCRIPTION_FILE "${CMAKE_CURRENT_SOURCE_DIR}/README.org")
set(CPACK_PACKAGE_VERSION_MAJOR "0")
set(CPACK_PACKAGE_VERSION_MINOR "5")
set(CPACK_PACKAGE_VERSION_PATCH "4")
set(CPACK_PACKAGE_VERSION_PATCH "0-beta4")
set(sdcv_VERSION
"${CPACK_PACKAGE_VERSION_MAJOR}.${CPACK_PACKAGE_VERSION_MINOR}.${CPACK_PACKAGE_VERSION_PATCH}")
@@ -138,16 +139,9 @@ if (BUILD_TESTS)
add_sdcv_shell_test(t_list)
add_sdcv_shell_test(t_use)
add_sdcv_shell_test(t_only_data_dir)
add_sdcv_shell_test(t_synonyms)
add_sdcv_shell_test(t_json)
add_sdcv_shell_test(t_exact)
add_sdcv_shell_test(t_interactive)
add_sdcv_shell_test(t_utf8output)
add_sdcv_shell_test(t_utf8input)
add_sdcv_shell_test(t_datadir)
add_sdcv_shell_test(t_return_code)
add_sdcv_shell_test(t_multiple_results)
add_sdcv_shell_test(t_newlines_in_ifo)
endif (BUILD_TESTS)

134
Cargo.lock generated Normal file
View File

@@ -0,0 +1,134 @@
[root]
name = "sdcv"
version = "0.1.0"
dependencies = [
"byteorder 0.5.3 (registry+https://github.com/rust-lang/crates.io-index)",
"flate2 0.2.14 (registry+https://github.com/rust-lang/crates.io-index)",
"getopts 0.2.14 (registry+https://github.com/rust-lang/crates.io-index)",
"gettext 0.2.0 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.14 (registry+https://github.com/rust-lang/crates.io-index)",
"rust-ini 0.9.5 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "byteorder"
version = "0.4.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "byteorder"
version = "0.5.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "encoding"
version = "0.2.32"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"encoding-index-japanese 1.20141219.5 (registry+https://github.com/rust-lang/crates.io-index)",
"encoding-index-korean 1.20141219.5 (registry+https://github.com/rust-lang/crates.io-index)",
"encoding-index-simpchinese 1.20141219.5 (registry+https://github.com/rust-lang/crates.io-index)",
"encoding-index-singlebyte 1.20141219.5 (registry+https://github.com/rust-lang/crates.io-index)",
"encoding-index-tradchinese 1.20141219.5 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "encoding-index-japanese"
version = "1.20141219.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"encoding_index_tests 0.1.4 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "encoding-index-korean"
version = "1.20141219.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"encoding_index_tests 0.1.4 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "encoding-index-simpchinese"
version = "1.20141219.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"encoding_index_tests 0.1.4 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "encoding-index-singlebyte"
version = "1.20141219.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"encoding_index_tests 0.1.4 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "encoding-index-tradchinese"
version = "1.20141219.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"encoding_index_tests 0.1.4 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "encoding_index_tests"
version = "0.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "flate2"
version = "0.2.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"libc 0.2.14 (registry+https://github.com/rust-lang/crates.io-index)",
"miniz-sys 0.1.7 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "gcc"
version = "0.3.28"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "getopts"
version = "0.2.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "gettext"
version = "0.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"byteorder 0.4.2 (registry+https://github.com/rust-lang/crates.io-index)",
"encoding 0.2.32 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "libc"
version = "0.2.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "log"
version = "0.3.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "miniz-sys"
version = "0.1.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"gcc 0.3.28 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.14 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "rust-ini"
version = "0.9.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"log 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
]

12
Cargo.toml Normal file
View File

@@ -0,0 +1,12 @@
[package]
name = "sdcv"
version = "0.1.0"
authors = ["Evgeniy A. Dushistov <dushistov@mail.ru>"]
[dependencies]
getopts = "0.2"
gettext = "0.2.0"
rust-ini = "0.9.5"
byteorder = "0.5"
libc = "0.2.14"
flate2 = "0.2"

11
LICENSE
View File

@@ -1,11 +1,10 @@
GNU GENERAL PUBLIC LICENSE
Version 2, June 1991
Copyright (C) 1989, 1991 Free Software Foundation, Inc.
51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Copyright (C) 1989, 1991 Free Software Foundation, Inc.
59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
@@ -306,7 +305,7 @@ the "copyright" line and a pointer to where the full notice is found.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
Also add information on how to contact you by electronic and paper mail.

18
NEWS
View File

@@ -1,21 +1,3 @@
Version 0.5.3
- Use single quotes around JSON data to reduce need for escaping
- Store integer magic in cache file
- Added $SDCV_HISTFILE to set history file
- return exit code 2 if search term not found
- Comply with the XDG Base Directory Specification
Version 0.5.2
- Synonyms index support (.syn files) by Peter <craven@gmx.net>
- Add support of json output by Peter <craven@gmx.net> (--json-output)
- Add -e for exact searches (no fuzzy matches) by Peter <craven@gmx.net>
- Fix build with clang 3.4.1
- fix FSF address in license by Tomáš Čech <sleep_walker@suse.com>
Version 0.5.1
Fix usage of SDCV_PAGER by Anton Yuzhaninov
Fix build without readline<
specify dictionary order by -u switches or ~/.sdcv_ordering by Cong Gu
Version 0.5
- add option to colorize output
- Roman Imankulov's patch to better use of readline

14
README.org
View File

@@ -1,5 +1,5 @@
#+OPTIONS: ^:nil
[[https://github.com/Dushistov/sdcv/actions?query=workflow%3ACI+branch%3Amaster][https://github.com/Dushistov/sdcv/workflows/CI/badge.svg]]
[[https://travis-ci.org/Dushistov/sdcv][https://travis-ci.org/Dushistov/sdcv.svg?branch=master]]
[[https://github.com/Dushistov/sdcv/blob/master/LICENSE][https://img.shields.io/badge/license-GPL%202-brightgreen.svg]]
* How to compile and install
#+BEGIN_SRC sh
@@ -22,20 +22,12 @@ you can use "DESTDIR" variable to change installation path
See sdcv man page for usage description.
* Bugs
To report bugs use https://github.com/Dushistov/sdcv/issues ,
if it is not possible you can report it via email to dushistov at mail dot ru.
If you find bug reports it via email to dushistov at mail dot ru.
Be sure to include the word "sdcv" somewhere in the "Subject:" field.
* Notes to developer
** make source code release
#+BEGIN_SRC sh
make package_source
#+END_SRC
** update translation
#+BEGIN_SRC sh
cd po
xgettext -k_ ../src/*.cpp -o new.pot
msgmerge -U sdcv.pot new.pot
rm new.pot
for i in `ls *.po`; do msgmerge -U $i sdcv.pot; done
#+END_SRC

13
cmake/compiler.cmake
View File

@@ -16,6 +16,19 @@ if (NOT DEFINED SDCV_COMPILER_IS_GCC_COMPATIBLE)
endif()
endif()
if (MSVC AND (MSVC_VERSION LESS 1900))
message(FATAL_ERROR "MSVC version ${MSVC_VERSION} have no full c++11 support")
elseif (MSVC)
add_definitions(-DNOMINMAX)
elseif (NOT MSVC)
check_cxx_compiler_flag("-std=c++11" CXX_SUPPORTS_CXX11)
if (CXX_SUPPORTS_CXX11)
append("-std=c++11" CMAKE_CXX_FLAGS)
else ()
message(FATAL_ERROR "sdcv requires C++11 support but the '-std=c++11' flag isn't supported.")
endif()
endif ()
if (SDCV_COMPILER_IS_GCC_COMPATIBLE)
append("-Wall" "-Wextra" "-Wformat-security" "-Wcast-align" "-Werror=format" "-Wcast-qual" CMAKE_C_FLAGS)
append("-Wall" "-pedantic" "-Wextra" "-Wformat-security" "-Wcast-align" "-Werror=format" "-Wcast-qual" CMAKE_CXX_FLAGS)

85
doc/sdcv.1
View File

@@ -9,95 +9,78 @@ sdcv \- console version of StarDict program
[list of words]
.SH DESCRIPTION
.I sdcv
is a simple, cross-platform text-based utility
for working with dictionaries in StarDict format.
Each word from "list of words" may be a string
with a leading '/' for using a Fuzzy search algorithm,
with a leading '|' for using full-text search,
and the string may contain '?' and '*' for regexp search.
It works in interactive and non-interactive mode.
is simple, cross-platform text-base utility
for work with dictionaries in StarDict's format.
The word from "list of words" may be string
with leading '/' for using Fuzzy search algorithm,
with leading '|' for using full-text search,
string may contain '?' and '*' for using regexp search.
It work in interactive and not interactive mode.
To exit from interactive mode press Ctrl+D.
In interactive mode,
if sdcv was compiled with readline library support,
you can use the UP and DOWN keys to cycle through history.
you can use UP and DOWN keys to work through history.
.SH OPTIONS
.TP 8
.B "\-h \-\-help"
Display help message and exit
display help message and exit
.TP 8
.B "\-v \-\-version"
Display version and exit
.B "\-v \-\-verbose"
display version and exit
.TP 8
.B "\-l \-\-list\-dicts"
Display list of available dictionaries and exit
display list of available dictionaries and exit
.TP 8
.B "\-u \-\-use\-dict filename"
For search use only dictionary with this bookname
for search use only dictionary with this bookname
.TP 8
.B "\-n \-\-non\-interactive"
For use in scripts
.TP 8
.B "\-x \-\-only\-data\-dir"
For use in scripts: only use the dictionaries in data-dir, do not search in user and system directories
.TP 8
.B "\-e \-\-exact\-search"
Do not fuzzy-search for similar words, only return exact matches
.TP 8
.B "\-j \-\-json"
Print the results of list-dicts and searches as json, not as plain text.
For use in automatically processing the results of a dictionary lookup.
for use in scripts
.TP 8
.B "\-\-utf8\-output"
Force sdcv to not convert to locale charset, output in utf8
Force sdcv not use conversation to locale charset, output in utf8
.TP 8
.B "\-\-utf8\-input"
Force sdcv to not convert from locale charset, assume that
input is in utf8
Force sdcv not use conversation from locale charset, suppose that
input in utf8
.TP 8
.B "\-\-data\-dir path/to/directory"
Use this directory as the path to the stardict data directory. This means that
sdcv searches for dictionaries in data-dir/dic directory.
Use this directory as path to stardict data directory. This is mean that
sdcv search dictionaries in data-dir/dic directory.
.TP 8
.B "\-\-color"
Use ANSI escape codes for colorizing sdcv output (does not work with json output).
Use ANSI escape code for colorize sdcv output
.SH FILES
.TP
/usr/share/stardict/dic
/usr/share/stardict/dic
.TP
$(XDG_DATA_HOME)/stardict/dic
$(HOME)/.stardict/dic
Place where sdcv expects to find dictionaries.
Instead of /usr/share/stardict/dic you can use any directory
you want, just set the STARDICT_DATA_DIR environment variable.
Place, where sdcv expect to find dictionaries.
Instead of /usr/share/stardict/dic you can use everything
that you want, just set STARDICT_DATA_DIR environment variable.
For example, if you have dictionaries in /mnt/data/stardict-dicts/dic,
set STARDICT_DATA_DIR to /mnt/data/stardict-dicts.
.TP
$(XDG_DATA_HOME)/sdcv_history
$(HOME)/.sdcv_history
This file includes the last $(SDCV_HISTSIZE) words, which you sought with sdcv.
SDCV uses this file only if it was compiled with readline library support.
.TP
$(XDG_CONFIG_HOME)/sdcv_ordering
This file include last $(SDCV_HISTSIZE) words, which you seek with sdcv.
SDCV use this file only if it was compiled with readline library support.
This is a text file containing one dictionary bookname per line.
It specifies in which order the results of a search should be shown.
.SH ENVIRONMENT
Environment Variables Used By \fIsdcv\fR:
.TP 20
.B STARDICT_DATA_DIR
If set, sdcv uses this variable as the data directory, this means that sdcv
searches dictionaries in $\fBSTARDICT_DATA_DIR\fR/dic
If set, sdcv use this variable as data directory, this is mean that sdcv
search dictionaries in $\fBSTARDICT_DATA_DIR\fR\\dic
.TP 20
.B SDCV_HISTSIZE
If set, sdcv writes in $(XDG_DATA_HOME)/sdcv_history (or $(SDCV_HISTFILE)) the last $(SDCV_HISTSIZE) words,
which you look up using sdcv. If it is not set, then the last 2000 words are saved in $(XDG_DATA_HOME)/sdcv_history.
.TP 20
.B SDCV_HISTFILE
If set, sdcv writes it's history to $(SDCV_HISTFILE). If it is not set, then the default $(XDG_DATA_HOME)/sdcv_history path will be used.
If set, sdcv wrote in $(HOME)/.sdcv_history only last $(SDCV_HISTSIZE) words,
which you seek using sdcv. If it is not set, then last 2000 words saved in $(HOME)/.sdcv_history.
.TP 20
.B SDCV_PAGER
If SDCV_PAGER is set, its value is used as the name of the program
to use to display the dictionary article.
If SDCV_PAGER is set, its value is used as the name of the program
to use to display the dictionary's article.
.SH BUGS
Email bug reports to dushistov at mail dot ru. Be sure to include the word
"sdcv" somewhere in the "Subject:" field.

10
doc/uk/sdcv.1
View File

@@ -50,7 +50,7 @@ sdcv проста, міжплатформена текстова утиліта
.TP
/usr/share/stardict/dic
.TP
$(XDG_DATA_HOME)/stardict/dic
$(HOME)/.stardict/dic
Місце, де sdcv очікує знайти словники.
Замість шляху /usr/share/stardict/dic Ви можете використовувати все,
@@ -58,7 +58,7 @@ $(XDG_DATA_HOME)/stardict/dic
Наприклад, якщо Ви маєте словники у теці /mnt/data/stardict-dicts/dic,
встановіть STARDICT_DATA_DIR у /mnt/data/stardict-dicts.
.TP
$(XDG_DATA_HOME)/sdcv_history
$(HOME)/.sdcv_history
Цей файл містить останні $(SDCV_HISTSIZE) слова, які Ви шукали з sdcv.
SDCV використовує цей файл при умові, якщо sdcv був скомпільований
@@ -69,12 +69,12 @@ SDCV використовує цей файл при умові, якщо sdcv
.TP 20
.B STARDICT_DATA_DIR
Якщо встановлена, sdcv використає цю змінну як теку даних, це означає,
що sdcv шукатиме словники у $\fBSTARDICT_DATA_DIR\fR/dic
що sdcv шукатиме словники у $\fBSTARDICT_DATA_DIR\fR\dic
.TP 20
.B SDCV_HISTSIZE
Якщо встановлена, sdcv писатиме у $(XDG_DATA_HOME)/sdcv_history лише
Якщо встановлена, sdcv писатиме у $(HOME)/.sdcv_history лише
останні $(SDCV_HISTSIZE) слова, які Ви шукали з sdcv. Якщо не встановлена,
то збірігатиметься останніх 2000 слів у $(XDG_DATA_HOME)/sdcv_history.
то збірігатиметься останніх 2000 слів у $(HOME)/.sdcv_history.
.SH BUGS
Звіти про помилки висилайте на адресу dushistov на mail крапка ru.
Не забувайте включати слово "sdcv" десь у полі "Тема:".

188
po/cs.po
View File

@@ -6,7 +6,7 @@ msgid ""
msgstr ""
"Project-Id-Version: sdcv 0.4.2\n"
"Report-Msgid-Bugs-To: dushistov@mail.ru\n"
"POT-Creation-Date: 2020-08-14 12:58+0300\n"
"POT-Creation-Date: 2008-09-24 10:54+0200\n"
"PO-Revision-Date: 2008-09-24 10:42+0200\n"
"Last-Translator: Michal Čihař <michal@cihar.com>\n"
"Language-Team: Czech <cs@li.org>\n"
@@ -16,25 +16,102 @@ msgstr ""
"Content-Transfer-Encoding: 8bit\n"
"Plural-Forms: nplurals=3; plural=(n==1) ? 0 : (n>=2 && n<=4) ? 1 : 2;\n"
#: ../src/libwrapper.cpp:300
#: src/sdcv.cpp:108
#, fuzzy
msgid "display version information and exit"
msgstr "-v, --version zobrazí informace o verzi a skončí\n"
#: src/sdcv.cpp:110
#, fuzzy
msgid "display list of available dictionaries and exit"
msgstr "-l, --list-dicts zobrazí seznam dostupných slovníků a skončí\n"
#: src/sdcv.cpp:112
#, fuzzy
msgid "for search use only dictionary with this bookname"
msgstr "-u, --use-dict jméno vyhledávat jen v zadaném slovníku\n"
#: src/sdcv.cpp:113
msgid "bookname"
msgstr ""
#: src/sdcv.cpp:115
msgid "for use in scripts"
msgstr ""
#: src/sdcv.cpp:117
#, fuzzy
msgid "output must be in utf8"
msgstr "--utf8-output výstup musí být v utf8\n"
#: src/sdcv.cpp:119
#, fuzzy
msgid "input of sdcv in utf8"
msgstr "--utf8-input vstup musí být v utf8\n"
#: src/sdcv.cpp:121
#, fuzzy
msgid "use this directory as path to stardict data directory"
msgstr ""
"--data-dir cesta/někam použít tento adresář jako cestu ke slovníkům "
"stardict\n"
#: src/sdcv.cpp:122
msgid "path/to/dir"
msgstr ""
#: src/sdcv.cpp:129
msgid " words"
msgstr ""
#: src/sdcv.cpp:135
#, c-format
msgid "Invalid command line arguments: %s\n"
msgstr ""
#: src/sdcv.cpp:141
#, c-format
msgid "Console version of Stardict, version %s\n"
msgstr "Konzolová verze Stardictu, verze %s\n"
#: src/sdcv.cpp:170
#, c-format
msgid "Dictionary's name Word count\n"
msgstr "Jméno slovníku Počet slov\n"
#: src/sdcv.cpp:192
#, c-format
msgid "g_mkdir failed: %s\n"
msgstr "g_mkdir selhalo: %s\n"
#: src/sdcv.cpp:208
msgid "Enter word or phrase: "
msgstr "Zadejte slovo nebo frázi: "
#: src/sdcv.cpp:216
#, c-format
msgid "There are no words/phrases to translate.\n"
msgstr "Nebyla zadáno nic k přeložení.\n"
#: src/libwrapper.cpp:248
msgid "popen failed"
msgstr "popen selhalo"
#: ../src/libwrapper.cpp:341
#: src/libwrapper.cpp:285 src/utils.cpp:67
#, c-format
msgid "Can not convert %s to utf8.\n"
msgstr "Nepodařilo se převést %s do utf8.\n"
#: ../src/libwrapper.cpp:399 ../src/libwrapper.cpp:433
#: src/libwrapper.cpp:342 src/libwrapper.cpp:370
#, fuzzy, c-format
msgid "Found %zu items, similar to %s.\n"
msgstr "Nalezeno %d záznamů podobných %s.\n"
#: ../src/libwrapper.cpp:417
#: src/libwrapper.cpp:356
msgid "Your choice[-1 to abort]: "
msgstr "Vaše volba [-1 pro ukončení]: "
#: ../src/libwrapper.cpp:427
#: src/libwrapper.cpp:365
#, fuzzy, c-format
msgid ""
"Invalid choice.\n"
@@ -43,107 +120,12 @@ msgstr ""
"Chybná volba.\n"
"Musí být mezi 0 a %d nebo -1.\n"
#: ../src/libwrapper.cpp:446
#: src/libwrapper.cpp:381
#, c-format
msgid "Nothing similar to %s, sorry :(\n"
msgstr "Nic podobného %s nenalezeno, promiň :(\n"
#: ../src/sdcv.cpp:89
#, fuzzy
msgid "display version information and exit"
msgstr "-v, --version zobrazí informace o verzi a skončí\n"
#: ../src/sdcv.cpp:91
#, fuzzy
msgid "display list of available dictionaries and exit"
msgstr "-l, --list-dicts zobrazí seznam dostupných slovníků a skončí\n"
#: ../src/sdcv.cpp:93
#, fuzzy
msgid "for search use only dictionary with this bookname"
msgstr "-u, --use-dict jméno vyhledávat jen v zadaném slovníku\n"
#: ../src/sdcv.cpp:94
msgid "bookname"
msgstr ""
#: ../src/sdcv.cpp:96
msgid "for use in scripts"
msgstr ""
#: ../src/sdcv.cpp:98
msgid "print the result formatted as JSON"
msgstr ""
#: ../src/sdcv.cpp:100
msgid "do not fuzzy-search for similar words, only return exact matches"
msgstr ""
#: ../src/sdcv.cpp:102
#, fuzzy
msgid "output must be in utf8"
msgstr "--utf8-output výstup musí být v utf8\n"
#: ../src/sdcv.cpp:104
#, fuzzy
msgid "input of sdcv in utf8"
msgstr "--utf8-input vstup musí být v utf8\n"
#: ../src/sdcv.cpp:106
#, fuzzy
msgid "use this directory as path to stardict data directory"
msgstr ""
"--data-dir cesta/někam použít tento adresář jako cestu ke slovníkům "
"stardict\n"
#: ../src/sdcv.cpp:107
msgid "path/to/dir"
msgstr ""
#: ../src/sdcv.cpp:109
msgid ""
"only use the dictionaries in data-dir, do not search in user and system "
"directories"
msgstr ""
#: ../src/sdcv.cpp:111
msgid "colorize the output"
msgstr ""
#: ../src/sdcv.cpp:116
msgid " words"
msgstr ""
#: ../src/sdcv.cpp:122
#, c-format
msgid "Invalid command line arguments: %s\n"
msgstr ""
#: ../src/sdcv.cpp:128
#, c-format
msgid "Console version of Stardict, version %s\n"
msgstr "Konzolová verze Stardictu, verze %s\n"
#: ../src/sdcv.cpp:206
#, c-format
msgid "g_mkdir failed: %s\n"
msgstr "g_mkdir selhalo: %s\n"
#: ../src/sdcv.cpp:222
msgid "Enter word or phrase: "
msgstr "Zadejte slovo nebo frázi: "
#: ../src/sdcv.cpp:230
#, c-format
msgid "There are no words/phrases to translate.\n"
msgstr "Nebyla zadáno nic k přeložení.\n"
#: ../src/sdcv.cpp:242
#, c-format
msgid "Dictionary's name Word count\n"
msgstr "Jméno slovníku Počet slov\n"
#: ../src/utils.cpp:48
#: src/utils.cpp:45
#, fuzzy, c-format
msgid "Can not convert %s to current locale.\n"
msgstr "Nepodařilo se převést %s do utf8.\n"

198
po/fr.po
View File

@@ -8,7 +8,7 @@ msgid ""
msgstr ""
"Project-Id-Version: sdcv 0.4.2\n"
"Report-Msgid-Bugs-To: dushistov@mail.ru\n"
"POT-Creation-Date: 2020-08-14 12:58+0300\n"
"POT-Creation-Date: 2008-09-24 10:54+0200\n"
"PO-Revision-Date: 2009-06-15 23:20+0800\n"
"Language-Team: Vincent Petry <PVince81@yahoo.fr>\n"
"Language: \n"
@@ -18,25 +18,107 @@ msgstr ""
"Plural-Forms: nplurals=3; plural=(n%10==1 && n%100!=11 ? 0 : n%10>=2 && n"
"%10<=4 && (n%100<10 || n%100>=20) ? 1 : 2);\n"
#: ../src/libwrapper.cpp:300
#: src/sdcv.cpp:108
#, fuzzy
msgid "display version information and exit"
msgstr ""
"-v, --version afficher les informations de version et sortir\n"
#: src/sdcv.cpp:110
#, fuzzy
msgid "display list of available dictionaries and exit"
msgstr ""
"-l, --list-dicts afficher la liste des dictionnaires disponibles et "
"sortir\n"
#: src/sdcv.cpp:112
#, fuzzy
msgid "for search use only dictionary with this bookname"
msgstr ""
"-u, --use-dict nom_dict pour chercher seulement en utilisant le "
"dictionnaire spécifié\n"
#: src/sdcv.cpp:113
msgid "bookname"
msgstr ""
#: src/sdcv.cpp:115
msgid "for use in scripts"
msgstr ""
#: src/sdcv.cpp:117
#, fuzzy
msgid "output must be in utf8"
msgstr "--utf8-output force la sortie au format utf8\n"
#: src/sdcv.cpp:119
#, fuzzy
msgid "input of sdcv in utf8"
msgstr "--utf8-input force l'entrée de sdcv au format utf8\n"
#: src/sdcv.cpp:121
#, fuzzy
msgid "use this directory as path to stardict data directory"
msgstr ""
"--data-dir chemin utiliser ce chemin pour trouver les données de "
"stardict\n"
#: src/sdcv.cpp:122
msgid "path/to/dir"
msgstr ""
#: src/sdcv.cpp:129
msgid " words"
msgstr ""
#: src/sdcv.cpp:135
#, c-format
msgid "Invalid command line arguments: %s\n"
msgstr ""
#: src/sdcv.cpp:141
#, c-format
msgid "Console version of Stardict, version %s\n"
msgstr "Version console de Stardict, version %s\n"
#: src/sdcv.cpp:170
#, c-format
msgid "Dictionary's name Word count\n"
msgstr "Nom dictionnaire Nombre de mots\n"
#: src/sdcv.cpp:192
#, c-format
msgid "g_mkdir failed: %s\n"
msgstr "Échec de g_mkdir : %s\n"
#: src/sdcv.cpp:208
msgid "Enter word or phrase: "
msgstr "Entrez un mot ou une phrase: "
#: src/sdcv.cpp:216
#, c-format
msgid "There are no words/phrases to translate.\n"
msgstr "Il n'y a pas de mots/phrases à traduire.\n"
#: src/libwrapper.cpp:248
msgid "popen failed"
msgstr "Échec de popen"
#: ../src/libwrapper.cpp:341
#: src/libwrapper.cpp:285 src/utils.cpp:67
#, c-format
msgid "Can not convert %s to utf8.\n"
msgstr "Ne peut convertir %s au format utf8.\n"
#: ../src/libwrapper.cpp:399 ../src/libwrapper.cpp:433
#: src/libwrapper.cpp:342 src/libwrapper.cpp:370
#, fuzzy, c-format
msgid "Found %zu items, similar to %s.\n"
msgstr "Trouvé %d éléments similaires à %s.\n"
#: ../src/libwrapper.cpp:417
#: src/libwrapper.cpp:356
msgid "Your choice[-1 to abort]: "
msgstr "Votre choix[-1 pour abandonner] : "
#: ../src/libwrapper.cpp:427
#: src/libwrapper.cpp:365
#, fuzzy, c-format
msgid ""
"Invalid choice.\n"
@@ -45,112 +127,12 @@ msgstr ""
"Selection invalide.\n"
"Veuillez choisir un nombre entre 0 et %d, ou -1.\n"
#: ../src/libwrapper.cpp:446
#: src/libwrapper.cpp:381
#, c-format
msgid "Nothing similar to %s, sorry :(\n"
msgstr "Aucun mot/phrase similaire à %s, désolé :(\n"
#: ../src/sdcv.cpp:89
#, fuzzy
msgid "display version information and exit"
msgstr ""
"-v, --version afficher les informations de version et sortir\n"
#: ../src/sdcv.cpp:91
#, fuzzy
msgid "display list of available dictionaries and exit"
msgstr ""
"-l, --list-dicts afficher la liste des dictionnaires disponibles et "
"sortir\n"
#: ../src/sdcv.cpp:93
#, fuzzy
msgid "for search use only dictionary with this bookname"
msgstr ""
"-u, --use-dict nom_dict pour chercher seulement en utilisant le "
"dictionnaire spécifié\n"
#: ../src/sdcv.cpp:94
msgid "bookname"
msgstr ""
#: ../src/sdcv.cpp:96
msgid "for use in scripts"
msgstr ""
#: ../src/sdcv.cpp:98
msgid "print the result formatted as JSON"
msgstr ""
#: ../src/sdcv.cpp:100
msgid "do not fuzzy-search for similar words, only return exact matches"
msgstr ""
#: ../src/sdcv.cpp:102
#, fuzzy
msgid "output must be in utf8"
msgstr "--utf8-output force la sortie au format utf8\n"
#: ../src/sdcv.cpp:104
#, fuzzy
msgid "input of sdcv in utf8"
msgstr "--utf8-input force l'entrée de sdcv au format utf8\n"
#: ../src/sdcv.cpp:106
#, fuzzy
msgid "use this directory as path to stardict data directory"
msgstr ""
"--data-dir chemin utiliser ce chemin pour trouver les données de "
"stardict\n"
#: ../src/sdcv.cpp:107
msgid "path/to/dir"
msgstr ""
#: ../src/sdcv.cpp:109
msgid ""
"only use the dictionaries in data-dir, do not search in user and system "
"directories"
msgstr ""
#: ../src/sdcv.cpp:111
msgid "colorize the output"
msgstr ""
#: ../src/sdcv.cpp:116
msgid " words"
msgstr ""
#: ../src/sdcv.cpp:122
#, c-format
msgid "Invalid command line arguments: %s\n"
msgstr ""
#: ../src/sdcv.cpp:128
#, c-format
msgid "Console version of Stardict, version %s\n"
msgstr "Version console de Stardict, version %s\n"
#: ../src/sdcv.cpp:206
#, c-format
msgid "g_mkdir failed: %s\n"
msgstr "Échec de g_mkdir : %s\n"
#: ../src/sdcv.cpp:222
msgid "Enter word or phrase: "
msgstr "Entrez un mot ou une phrase: "
#: ../src/sdcv.cpp:230
#, c-format
msgid "There are no words/phrases to translate.\n"
msgstr "Il n'y a pas de mots/phrases à traduire.\n"
#: ../src/sdcv.cpp:242
#, c-format
msgid "Dictionary's name Word count\n"
msgstr "Nom dictionnaire Nombre de mots\n"
#: ../src/utils.cpp:48
#: src/utils.cpp:45
#, c-format
msgid "Can not convert %s to current locale.\n"
msgstr "Ne peut pas convertir %s dans la locale courante.\n"

183
po/ru.po
View File

@@ -8,8 +8,8 @@ msgid ""
msgstr ""
"Project-Id-Version: sdcv 0.5\n"
"Report-Msgid-Bugs-To: dushistov@mail.ru\n"
"POT-Creation-Date: 2020-08-14 12:58+0300\n"
"PO-Revision-Date: 2017-08-16 10:05+0300\n"
"POT-Creation-Date: 2008-09-24 10:54+0200\n"
"PO-Revision-Date: 2013-07-07 18:49+0400\n"
"Last-Translator: Evgeniy Dushistov <dushistov@mail.ru>\n"
"Language-Team: Russian <ru@li.org>\n"
"Language: ru\n"
@@ -19,25 +19,99 @@ msgstr ""
"Plural-Forms: nplurals=3; plural=(n%10==1 && n%100!=11 ? 0 : n%10>=2 && n"
"%10<=4 && (n%100<10 || n%100>=20) ? 1 : 2);\n"
#: ../src/libwrapper.cpp:300
#: src/sdcv.cpp:80
msgid "display version information and exit"
msgstr "показать номер версии и завершить работу"
#: src/sdcv.cpp:82
msgid "display list of available dictionaries and exit"
msgstr "показать список доступных словарей и завершить работу"
#: src/sdcv.cpp:84
msgid "for search use only dictionary with this bookname"
msgstr "для поиска использовать только этот словарь с таким именем"
#: src/sdcv.cpp:85
msgid "bookname"
msgstr "имя_словаря"
#: src/sdcv.cpp:87
msgid "for use in scripts"
msgstr "для использования в скриптах"
#: src/sdcv.cpp:89
msgid "output must be in utf8"
msgstr "вывод программы должен быть в utf8"
#: src/sdcv.cpp:91
msgid "input of sdcv in utf8"
msgstr "ввод программы в utf8"
#: src/sdcv.cpp:93
msgid "use this directory as path to stardict data directory"
msgstr ""
"использовать эту директорию в качестве пути к \"stardict data\" директории"
#: src/sdcv.cpp:94
msgid "path/to/dir"
msgstr "путь/до/директории"
#: src/sdcv.cpp:96
msgid "colorize the output"
msgstr "раскрашивать вывод в разные цвета"
#: src/sdcv.cpp:101
msgid " words"
msgstr "слова"
#: src/sdcv.cpp:107
#, c-format
msgid "Invalid command line arguments: %s\n"
msgstr "Неправильный аргумент командой строки: %s\n"
#: src/sdcv.cpp:113
#, c-format
msgid "Console version of Stardict, version %s\n"
msgstr "Консольная версия StarDict, версия %s\n"
#: src/sdcv.cpp:139
#, c-format
msgid "Dictionary's name Word count\n"
msgstr "Название словаря Количество слов\n"
#: src/sdcv.cpp:174
#, c-format
msgid "g_mkdir failed: %s\n"
msgstr "g_mkdir завершился с ошибкой: %s\n"
#: src/sdcv.cpp:189
msgid "Enter word or phrase: "
msgstr "Введите слово или фразу: "
#: src/sdcv.cpp:197
#, c-format
msgid "There are no words/phrases to translate.\n"
msgstr "Не задано слова/фразы для перевода.\n"
#: src/libwrapper.cpp:280
msgid "popen failed"
msgstr "функция popen завершилась с ошибкой"
#: ../src/libwrapper.cpp:341
#: src/libwrapper.cpp:317 src/utils.cpp:67
#, c-format
msgid "Can not convert %s to utf8.\n"
msgstr "Не могу преобразовать %s в utf8.\n"
#: ../src/libwrapper.cpp:399 ../src/libwrapper.cpp:433
#: src/libwrapper.cpp:371 src/libwrapper.cpp:402
#, c-format
msgid "Found %zu items, similar to %s.\n"
msgstr "Найдено %zu слов, похожих на %s.\n"
#: ../src/libwrapper.cpp:417
#: src/libwrapper.cpp:388
msgid "Your choice[-1 to abort]: "
msgstr "Ваш выбор[-1 - отмена]: "
#: ../src/libwrapper.cpp:427
#: src/libwrapper.cpp:397
#, c-format
msgid ""
"Invalid choice.\n"
@@ -46,103 +120,12 @@ msgstr ""
"Неправильный выбор.\n"
"Должно быть от 0 до %zu или -1.\n"
#: ../src/libwrapper.cpp:446
#: src/libwrapper.cpp:413
#, c-format
msgid "Nothing similar to %s, sorry :(\n"
msgstr "Ничего похожего на %s, извините :(\n"
#: ../src/sdcv.cpp:89
msgid "display version information and exit"
msgstr "показать номер версии и завершить работу"
#: ../src/sdcv.cpp:91
msgid "display list of available dictionaries and exit"
msgstr "показать список доступных словарей и завершить работу"
#: ../src/sdcv.cpp:93
msgid "for search use only dictionary with this bookname"
msgstr "для поиска использовать только этот словарь с таким именем"
#: ../src/sdcv.cpp:94
msgid "bookname"
msgstr "имя_словаря"
#: ../src/sdcv.cpp:96
msgid "for use in scripts"
msgstr "для использования в скриптах"
#: ../src/sdcv.cpp:98
msgid "print the result formatted as JSON"
msgstr "выдать результат в JSON формате"
#: ../src/sdcv.cpp:100
msgid "do not fuzzy-search for similar words, only return exact matches"
msgstr ""
"не использовать нечеткий поиск похожих слов, вернуть только точные совпадения"
#: ../src/sdcv.cpp:102
msgid "output must be in utf8"
msgstr "вывод программы должен быть в utf8"
#: ../src/sdcv.cpp:104
msgid "input of sdcv in utf8"
msgstr "ввод программы в utf8"
#: ../src/sdcv.cpp:106
msgid "use this directory as path to stardict data directory"
msgstr ""
"использовать эту директорию в качестве пути к \"stardict data\" директории"
#: ../src/sdcv.cpp:107
msgid "path/to/dir"
msgstr "путь/до/директории"
#: ../src/sdcv.cpp:109
msgid ""
"only use the dictionaries in data-dir, do not search in user and system "
"directories"
msgstr ""
"использовать словари только из data-dir, не искать в пользовательских и "
"системных каталогах"
#: ../src/sdcv.cpp:111
msgid "colorize the output"
msgstr "раскрашивать вывод в разные цвета"
#: ../src/sdcv.cpp:116
msgid " words"
msgstr "слова"
#: ../src/sdcv.cpp:122
#, c-format
msgid "Invalid command line arguments: %s\n"
msgstr "Неправильный аргумент командой строки: %s\n"
#: ../src/sdcv.cpp:128
#, c-format
msgid "Console version of Stardict, version %s\n"
msgstr "Консольная версия StarDict, версия %s\n"
#: ../src/sdcv.cpp:206
#, c-format
msgid "g_mkdir failed: %s\n"
msgstr "g_mkdir завершился с ошибкой: %s\n"
#: ../src/sdcv.cpp:222
msgid "Enter word or phrase: "
msgstr "Введите слово или фразу: "
#: ../src/sdcv.cpp:230
#, c-format
msgid "There are no words/phrases to translate.\n"
msgstr "Не задано слова/фразы для перевода.\n"
#: ../src/sdcv.cpp:242
#, c-format
msgid "Dictionary's name Word count\n"
msgstr "Название словаря Количество слов\n"
#: ../src/utils.cpp:48
#: src/utils.cpp:45
#, c-format
msgid "Can not convert %s to current locale.\n"
msgstr "Не могу преобразовать %s в локальную кодировку.\n"

179
po/sdcv.pot
View File

@@ -7,133 +7,118 @@ msgid ""
msgstr ""
"Project-Id-Version: sdcv 0.5\n"
"Report-Msgid-Bugs-To: dushistov@mail.ru\n"
"POT-Creation-Date: 2020-08-14 12:58+0300\n"
"PO-Revision-Date: 2017-08-16 10:01+0300\n"
"POT-Creation-Date: 2008-09-24 10:54+0200\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language-Team: LANGUAGE <LL@li.org>\n"
"Language: \n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=CHARSET\n"
"Content-Transfer-Encoding: 8bit\n"
#: ../src/libwrapper.cpp:300
#: src/sdcv.cpp:76
msgid "display version information and exit"
msgstr ""
#: src/sdcv.cpp:78
msgid "display list of available dictionaries and exit"
msgstr ""
#: src/sdcv.cpp:84
msgid "for search use only dictionary with this bookname"
msgstr ""
#: src/sdcv.cpp:85
msgid "bookname"
msgstr ""
#: src/sdcv.cpp:87
msgid "for use in scripts"
msgstr ""
#: src/sdcv.cpp:89
msgid "output must be in utf8"
msgstr ""
#: src/sdcv.cpp:91
msgid "input of sdcv in utf8"
msgstr ""
#: src/sdcv.cpp:93
msgid "use this directory as path to stardict data directory"
msgstr ""
#: src/sdcv.cpp:94
msgid "path/to/dir"
msgstr ""
#: src/sdcv.cpp:96
msgid "colorize the output"
msgstr ""
#: src/sdcv.cpp:101
msgid " words"
msgstr ""
#: src/sdcv.cpp:107
#, c-format
msgid "Invalid command line arguments: %s\n"
msgstr ""
#: src/sdcv.cpp:113
#, c-format
msgid "Console version of Stardict, version %s\n"
msgstr ""
#: src/sdcv.cpp:139
#, c-format
msgid "Dictionary's name Word count\n"
msgstr ""
#: src/sdcv.cpp:174
#, c-format
msgid "g_mkdir failed: %s\n"
msgstr ""
#: src/sdcv.cpp:189
msgid "Enter word or phrase: "
msgstr ""
#: src/sdcv.cpp:197
#, c-format
msgid "There are no words/phrases to translate.\n"
msgstr ""
#: src/libwrapper.cpp:280
msgid "popen failed"
msgstr ""
#: ../src/libwrapper.cpp:341
#: src/libwrapper.cpp:317 src/utils.cpp:67
#, c-format
msgid "Can not convert %s to utf8.\n"
msgstr ""
#: ../src/libwrapper.cpp:399 ../src/libwrapper.cpp:433
#: src/libwrapper.cpp:371 src/libwrapper.cpp:402
#, c-format
msgid "Found %zu items, similar to %s.\n"
msgstr ""
#: ../src/libwrapper.cpp:417
#: src/libwrapper.cpp:388
msgid "Your choice[-1 to abort]: "
msgstr ""
#: ../src/libwrapper.cpp:427
#: src/libwrapper.cpp:397
#, c-format
msgid ""
"Invalid choice.\n"
"It must be from 0 to %zu or -1.\n"
msgstr ""
#: ../src/libwrapper.cpp:446
#: src/libwrapper.cpp:413
#, c-format
msgid "Nothing similar to %s, sorry :(\n"
msgstr ""
#: ../src/sdcv.cpp:89
msgid "display version information and exit"
msgstr ""
#: ../src/sdcv.cpp:91
msgid "display list of available dictionaries and exit"
msgstr ""
#: ../src/sdcv.cpp:93
msgid "for search use only dictionary with this bookname"
msgstr ""
#: ../src/sdcv.cpp:94
msgid "bookname"
msgstr ""
#: ../src/sdcv.cpp:96
msgid "for use in scripts"
msgstr ""
#: ../src/sdcv.cpp:98
msgid "print the result formatted as JSON"
msgstr ""
#: ../src/sdcv.cpp:100
msgid "do not fuzzy-search for similar words, only return exact matches"
msgstr ""
#: ../src/sdcv.cpp:102
msgid "output must be in utf8"
msgstr ""
#: ../src/sdcv.cpp:104
msgid "input of sdcv in utf8"
msgstr ""
#: ../src/sdcv.cpp:106
msgid "use this directory as path to stardict data directory"
msgstr ""
#: ../src/sdcv.cpp:107
msgid "path/to/dir"
msgstr ""
#: ../src/sdcv.cpp:109
msgid ""
"only use the dictionaries in data-dir, do not search in user and system "
"directories"
msgstr ""
#: ../src/sdcv.cpp:111
msgid "colorize the output"
msgstr ""
#: ../src/sdcv.cpp:116
msgid " words"
msgstr ""
#: ../src/sdcv.cpp:122
#, c-format
msgid "Invalid command line arguments: %s\n"
msgstr ""
#: ../src/sdcv.cpp:128
#, c-format
msgid "Console version of Stardict, version %s\n"
msgstr ""
#: ../src/sdcv.cpp:206
#, c-format
msgid "g_mkdir failed: %s\n"
msgstr ""
#: ../src/sdcv.cpp:222
msgid "Enter word or phrase: "
msgstr ""
#: ../src/sdcv.cpp:230
#, c-format
msgid "There are no words/phrases to translate.\n"
msgstr ""
#: ../src/sdcv.cpp:242
#, c-format
msgid "Dictionary's name Word count\n"
msgstr ""
#: ../src/utils.cpp:48
#: src/utils.cpp:45
#, c-format
msgid "Can not convert %s to current locale.\n"
msgstr ""

190
po/sk.po
View File

@@ -6,7 +6,7 @@ msgid ""
msgstr ""
"Project-Id-Version: sdcv 0.3.2\n"
"Report-Msgid-Bugs-To: dushistov@mail.ru\n"
"POT-Creation-Date: 2020-08-14 12:58+0300\n"
"POT-Creation-Date: 2008-09-24 10:54+0200\n"
"PO-Revision-Date: 2007-09-11 00:22+0100\n"
"Last-Translator: Ivan Masár <helix84@centrum.sk>\n"
"Language-Team: Slovak <sk-i18n@lists.linux.sk>\n"
@@ -18,26 +18,104 @@ msgstr ""
"Plural-Forms: nplurals=3; plural=(n%10==1 && n%100!=11 ? 0 : n%10>=2 && n"
"%10<=4 && (n%100<10 || n%100>=20) ? 1 : 2);\n"
#: ../src/libwrapper.cpp:300
#: src/sdcv.cpp:108
#, fuzzy
msgid "display version information and exit"
msgstr "-v, --version zobrazí informácie o verzii a skončí\n"
#: src/sdcv.cpp:110
#, fuzzy
msgid "display list of available dictionaries and exit"
msgstr ""
"-l, --list-dicts zobrazí zoznam dostupných slovníkov a skončí\n"
#: src/sdcv.cpp:112
#, fuzzy
msgid "for search use only dictionary with this bookname"
msgstr "-u, --use-dict názov použiť pre hľadanie iba zvolený slovník\n"
#: src/sdcv.cpp:113
msgid "bookname"
msgstr ""
#: src/sdcv.cpp:115
msgid "for use in scripts"
msgstr ""
#: src/sdcv.cpp:117
#, fuzzy
msgid "output must be in utf8"
msgstr "--utf8-output výstup musí byť v utf8\n"
#: src/sdcv.cpp:119
#, fuzzy
msgid "input of sdcv in utf8"
msgstr "--utf8-input vstup pre sdcv je v utf8\n"
#: src/sdcv.cpp:121
#, fuzzy
msgid "use this directory as path to stardict data directory"
msgstr ""
"--data-dir path/to/dir použiť tento priečinok ako cestu pre stardict "
"dátový priečinok\n"
#: src/sdcv.cpp:122
msgid "path/to/dir"
msgstr ""
#: src/sdcv.cpp:129
msgid " words"
msgstr ""
#: src/sdcv.cpp:135
#, c-format
msgid "Invalid command line arguments: %s\n"
msgstr ""
#: src/sdcv.cpp:141
#, c-format
msgid "Console version of Stardict, version %s\n"
msgstr "Konzolová verzia StarDict, verzia %s\n"
#: src/sdcv.cpp:170
#, c-format
msgid "Dictionary's name Word count\n"
msgstr "názov slovníka počet slov\n"
#: src/sdcv.cpp:192
#, c-format
msgid "g_mkdir failed: %s\n"
msgstr "g_mkdir zlyhalo: %s\n"
#: src/sdcv.cpp:208
msgid "Enter word or phrase: "
msgstr "Vložte slovo alebo frázu: "
#: src/sdcv.cpp:216
#, c-format
msgid "There are no words/phrases to translate.\n"
msgstr "Nie je čo preložiť.\n"
#: src/libwrapper.cpp:248
msgid "popen failed"
msgstr "popen zlyhalo"
#: ../src/libwrapper.cpp:341
#: src/libwrapper.cpp:285 src/utils.cpp:67
#, c-format
msgid "Can not convert %s to utf8.\n"
msgstr "nie je možné konvertovať %s na utf8.\n"
#: ../src/libwrapper.cpp:399 ../src/libwrapper.cpp:433
#: src/libwrapper.cpp:342 src/libwrapper.cpp:370
#, fuzzy, c-format
msgid "Found %zu items, similar to %s.\n"
msgstr "Nájdené %d položiek, podobných %s,\n"
#: ../src/libwrapper.cpp:417
#: src/libwrapper.cpp:356
#, fuzzy
msgid "Your choice[-1 to abort]: "
msgstr "Vaša voľba[-1 zruší]: "
#: ../src/libwrapper.cpp:427
#: src/libwrapper.cpp:365
#, fuzzy, c-format
msgid ""
"Invalid choice.\n"
@@ -46,108 +124,12 @@ msgstr ""
"Neplatná voľba.\n"
"Musí byť od 0 do %d alebo -1.\n"
#: ../src/libwrapper.cpp:446
#: src/libwrapper.cpp:381
#, c-format
msgid "Nothing similar to %s, sorry :(\n"
msgstr "Ľutujem, nič sa nepodobá na %s :(\n"
#: ../src/sdcv.cpp:89
#, fuzzy
msgid "display version information and exit"
msgstr "-v, --version zobrazí informácie o verzii a skončí\n"
#: ../src/sdcv.cpp:91
#, fuzzy
msgid "display list of available dictionaries and exit"
msgstr ""
"-l, --list-dicts zobrazí zoznam dostupných slovníkov a skončí\n"
#: ../src/sdcv.cpp:93
#, fuzzy
msgid "for search use only dictionary with this bookname"
msgstr "-u, --use-dict názov použiť pre hľadanie iba zvolený slovník\n"
#: ../src/sdcv.cpp:94
msgid "bookname"
msgstr ""
#: ../src/sdcv.cpp:96
msgid "for use in scripts"
msgstr ""
#: ../src/sdcv.cpp:98
msgid "print the result formatted as JSON"
msgstr ""
#: ../src/sdcv.cpp:100
msgid "do not fuzzy-search for similar words, only return exact matches"
msgstr ""
#: ../src/sdcv.cpp:102
#, fuzzy
msgid "output must be in utf8"
msgstr "--utf8-output výstup musí byť v utf8\n"
#: ../src/sdcv.cpp:104
#, fuzzy
msgid "input of sdcv in utf8"
msgstr "--utf8-input vstup pre sdcv je v utf8\n"
#: ../src/sdcv.cpp:106
#, fuzzy
msgid "use this directory as path to stardict data directory"
msgstr ""
"--data-dir path/to/dir použiť tento priečinok ako cestu pre stardict "
"dátový priečinok\n"
#: ../src/sdcv.cpp:107
msgid "path/to/dir"
msgstr ""
#: ../src/sdcv.cpp:109
msgid ""
"only use the dictionaries in data-dir, do not search in user and system "
"directories"
msgstr ""
#: ../src/sdcv.cpp:111
msgid "colorize the output"
msgstr ""
#: ../src/sdcv.cpp:116
msgid " words"
msgstr ""
#: ../src/sdcv.cpp:122
#, c-format
msgid "Invalid command line arguments: %s\n"
msgstr ""
#: ../src/sdcv.cpp:128
#, c-format
msgid "Console version of Stardict, version %s\n"
msgstr "Konzolová verzia StarDict, verzia %s\n"
#: ../src/sdcv.cpp:206
#, c-format
msgid "g_mkdir failed: %s\n"
msgstr "g_mkdir zlyhalo: %s\n"
#: ../src/sdcv.cpp:222
msgid "Enter word or phrase: "
msgstr "Vložte slovo alebo frázu: "
#: ../src/sdcv.cpp:230
#, c-format
msgid "There are no words/phrases to translate.\n"
msgstr "Nie je čo preložiť.\n"
#: ../src/sdcv.cpp:242
#, c-format
msgid "Dictionary's name Word count\n"
msgstr "názov slovníka počet slov\n"
#: ../src/utils.cpp:48
#: src/utils.cpp:45
#, c-format
msgid "Can not convert %s to current locale.\n"
msgstr "Nie je možné konvertovať %s na aktuálne locale.\n"

194
po/uk.po
View File

@@ -8,7 +8,7 @@ msgid ""
msgstr ""
"Project-Id-Version: sdcv 0.3\n"
"Report-Msgid-Bugs-To: dushistov@mail.ru\n"
"POT-Creation-Date: 2020-08-14 12:58+0300\n"
"POT-Creation-Date: 2008-09-24 10:54+0200\n"
"PO-Revision-Date: 2004-12-14 17:54+0300\n"
"Last-Translator: <dubyk@lsl.lviv.ua>\n"
"Language-Team: Ukrainian <dubyk@lsl.lviv.ua>\n"
@@ -19,26 +19,106 @@ msgstr ""
"Plural-Forms: nplurals=3; plural=(n%10==1 && n%100!=11 ? 0 : n%10>=2 && n"
"%10<=4 && (n%100<10 || n%100>=20) ? 1 : 2);\n"
#: ../src/libwrapper.cpp:300
#: src/sdcv.cpp:108
#, fuzzy
msgid "display version information and exit"
msgstr "-v, --version показати номер версії і завершити роботу\n"
#: src/sdcv.cpp:110
#, fuzzy
msgid "display list of available dictionaries and exit"
msgstr ""
"-l, --list-dicts показати список доступних словників і завершити "
"роботу\n"
#: src/sdcv.cpp:112
#, fuzzy
msgid "for search use only dictionary with this bookname"
msgstr ""
"-u, --use-dict ім`я словника для пошуку використовувати лише цей словник\n"
#: src/sdcv.cpp:113
msgid "bookname"
msgstr ""
#: src/sdcv.cpp:115
msgid "for use in scripts"
msgstr ""
#: src/sdcv.cpp:117
#, fuzzy
msgid "output must be in utf8"
msgstr "--utf8-output вивід програми повинен бути в utf8\n"
#: src/sdcv.cpp:119
#, fuzzy
msgid "input of sdcv in utf8"
msgstr "--utf8-input ввід програми в utf8\n"
#: src/sdcv.cpp:121
#, fuzzy
msgid "use this directory as path to stardict data directory"
msgstr ""
"--data-dir тека використовувати цю теку як шлях до stardict data "
"directory\n"
#: src/sdcv.cpp:122
msgid "path/to/dir"
msgstr ""
#: src/sdcv.cpp:129
msgid " words"
msgstr ""
#: src/sdcv.cpp:135
#, c-format
msgid "Invalid command line arguments: %s\n"
msgstr ""
#: src/sdcv.cpp:141
#, c-format
msgid "Console version of Stardict, version %s\n"
msgstr "Консольна версія Зоряного словника [Stardict], номер версії %s\n"
#: src/sdcv.cpp:170
#, fuzzy, c-format
msgid "Dictionary's name Word count\n"
msgstr "назва словника кількість слів\n"
#: src/sdcv.cpp:192
#, c-format
msgid "g_mkdir failed: %s\n"
msgstr ""
#: src/sdcv.cpp:208
msgid "Enter word or phrase: "
msgstr "ВведЁть слово або фразу: "
#: src/sdcv.cpp:216
#, c-format
msgid "There are no words/phrases to translate.\n"
msgstr "Не задано слова/фрази для перекладу.\n"
#: src/libwrapper.cpp:248
msgid "popen failed"
msgstr ""
#: ../src/libwrapper.cpp:341
#: src/libwrapper.cpp:285 src/utils.cpp:67
#, c-format
msgid "Can not convert %s to utf8.\n"
msgstr "Не можу перетворити %s у utf8.\n"
#: ../src/libwrapper.cpp:399 ../src/libwrapper.cpp:433
#: src/libwrapper.cpp:342 src/libwrapper.cpp:370
#, fuzzy, c-format
msgid "Found %zu items, similar to %s.\n"
msgstr "Знайдено %d слів, схожих на %s.\n"
#: ../src/libwrapper.cpp:417
#: src/libwrapper.cpp:356
#, fuzzy
msgid "Your choice[-1 to abort]: "
msgstr "Ваш вибір: "
#: ../src/libwrapper.cpp:427
#: src/libwrapper.cpp:365
#, fuzzy, c-format
msgid ""
"Invalid choice.\n"
@@ -47,110 +127,12 @@ msgstr ""
"Неправильний вибір.\n"
"Повинно бути від 0 до %d.\n"
#: ../src/libwrapper.cpp:446
#: src/libwrapper.cpp:381
#, c-format
msgid "Nothing similar to %s, sorry :(\n"
msgstr "Нічого схожого на %s, даруйте :(\n"
#: ../src/sdcv.cpp:89
#, fuzzy
msgid "display version information and exit"
msgstr "-v, --version показати номер версії і завершити роботу\n"
#: ../src/sdcv.cpp:91
#, fuzzy
msgid "display list of available dictionaries and exit"
msgstr ""
"-l, --list-dicts показати список доступних словників і завершити "
"роботу\n"
#: ../src/sdcv.cpp:93
#, fuzzy
msgid "for search use only dictionary with this bookname"
msgstr ""
"-u, --use-dict ім`я словника для пошуку використовувати лише цей словник\n"
#: ../src/sdcv.cpp:94
msgid "bookname"
msgstr ""
#: ../src/sdcv.cpp:96
msgid "for use in scripts"
msgstr ""
#: ../src/sdcv.cpp:98
msgid "print the result formatted as JSON"
msgstr ""
#: ../src/sdcv.cpp:100
msgid "do not fuzzy-search for similar words, only return exact matches"
msgstr ""
#: ../src/sdcv.cpp:102
#, fuzzy
msgid "output must be in utf8"
msgstr "--utf8-output вивід програми повинен бути в utf8\n"
#: ../src/sdcv.cpp:104
#, fuzzy
msgid "input of sdcv in utf8"
msgstr "--utf8-input ввід програми в utf8\n"
#: ../src/sdcv.cpp:106
#, fuzzy
msgid "use this directory as path to stardict data directory"
msgstr ""
"--data-dir тека використовувати цю теку як шлях до stardict data "
"directory\n"
#: ../src/sdcv.cpp:107
msgid "path/to/dir"
msgstr ""
#: ../src/sdcv.cpp:109
msgid ""
"only use the dictionaries in data-dir, do not search in user and system "
"directories"
msgstr ""
#: ../src/sdcv.cpp:111
msgid "colorize the output"
msgstr ""
#: ../src/sdcv.cpp:116
msgid " words"
msgstr ""
#: ../src/sdcv.cpp:122
#, c-format
msgid "Invalid command line arguments: %s\n"
msgstr ""
#: ../src/sdcv.cpp:128
#, c-format
msgid "Console version of Stardict, version %s\n"
msgstr "Консольна версія Зоряного словника [Stardict], номер версії %s\n"
#: ../src/sdcv.cpp:206
#, c-format
msgid "g_mkdir failed: %s\n"
msgstr ""
#: ../src/sdcv.cpp:222
msgid "Enter word or phrase: "
msgstr "ВведЁть слово або фразу: "
#: ../src/sdcv.cpp:230
#, c-format
msgid "There are no words/phrases to translate.\n"
msgstr "Не задано слова/фрази для перекладу.\n"
#: ../src/sdcv.cpp:242
#, fuzzy, c-format
msgid "Dictionary's name Word count\n"
msgstr "назва словника кількість слів\n"
#: ../src/utils.cpp:48
#: src/utils.cpp:45
#, c-format
msgid "Can not convert %s to current locale.\n"
msgstr "Не можу перетворити %s у локальне кодування.\n"

184
po/zh_CN.po
View File

@@ -6,7 +6,7 @@ msgid ""
msgstr ""
"Project-Id-Version: sdcv 0.3\n"
"Report-Msgid-Bugs-To: dushistov@mail.ru\n"
"POT-Creation-Date: 2020-08-14 12:58+0300\n"
"POT-Creation-Date: 2008-09-24 10:54+0200\n"
"PO-Revision-Date: 2005-1-17 00:58+0800\n"
"Last-Translator: Cai Qian <caiqian@gnome.org>\n"
"Language-Team: Simplified Chinese\n"
@@ -15,26 +15,101 @@ msgstr ""
"Content-Type: text/plain; charset=UTF-8\n"
"Content-Transfer-Encoding: 8bit\n"
#: ../src/libwrapper.cpp:300
#: src/sdcv.cpp:108
#, fuzzy
msgid "display version information and exit"
msgstr "-v, --version 显示版本信息并退出\n"
#: src/sdcv.cpp:110
#, fuzzy
msgid "display list of available dictionaries and exit"
msgstr "-l, --list-dicts 显示可用的字典列表并退出\n"
#: src/sdcv.cpp:112
#, fuzzy
msgid "for search use only dictionary with this bookname"
msgstr "-u, --use-dict 字典名 只使用指定的字典进行单词搜索\n"
#: src/sdcv.cpp:113
msgid "bookname"
msgstr ""
#: src/sdcv.cpp:115
msgid "for use in scripts"
msgstr ""
#: src/sdcv.cpp:117
#, fuzzy
msgid "output must be in utf8"
msgstr "--utf8-output 输出必须是 UTF-8\n"
#: src/sdcv.cpp:119
#, fuzzy
msgid "input of sdcv in utf8"
msgstr "--utf8-input sdcv 的输入为 UTF-8\n"
#: src/sdcv.cpp:121
#, fuzzy
msgid "use this directory as path to stardict data directory"
msgstr "--data-dir 目录路径 指定 Stardict 数据所在目录的路径\n"
#: src/sdcv.cpp:122
msgid "path/to/dir"
msgstr ""
#: src/sdcv.cpp:129
msgid " words"
msgstr ""
#: src/sdcv.cpp:135
#, c-format
msgid "Invalid command line arguments: %s\n"
msgstr ""
#: src/sdcv.cpp:141
#, c-format
msgid "Console version of Stardict, version %s\n"
msgstr "Stardict 的控制台版本，版本为 %s\n"
#: src/sdcv.cpp:170
#, fuzzy, c-format
msgid "Dictionary's name Word count\n"
msgstr "字典名 单词量\n"
#: src/sdcv.cpp:192
#, c-format
msgid "g_mkdir failed: %s\n"
msgstr ""
#: src/sdcv.cpp:208
msgid "Enter word or phrase: "
msgstr "请输入单词或短语："
#: src/sdcv.cpp:216
#, c-format
msgid "There are no words/phrases to translate.\n"
msgstr "没有供翻译的单词或短语。\n"
#: src/libwrapper.cpp:248
msgid "popen failed"
msgstr ""
#: ../src/libwrapper.cpp:341
#: src/libwrapper.cpp:285 src/utils.cpp:67
#, c-format
msgid "Can not convert %s to utf8.\n"
msgstr "无法将 %s 转换为 UTF-8。\n"
#: ../src/libwrapper.cpp:399 ../src/libwrapper.cpp:433
#: src/libwrapper.cpp:342 src/libwrapper.cpp:370
#, fuzzy, c-format
msgid "Found %zu items, similar to %s.\n"
msgstr "发现 %d 条记录和 %s 相似。\n"
#: ../src/libwrapper.cpp:417
#: src/libwrapper.cpp:356
#, fuzzy
msgid "Your choice[-1 to abort]: "
msgstr "您的选择为："
#: ../src/libwrapper.cpp:427
#: src/libwrapper.cpp:365
#, fuzzy, c-format
msgid ""
"Invalid choice.\n"
@@ -43,105 +118,12 @@ msgstr ""
"无效的选择。\n"
"必须是 0 到 %d。\n"
#: ../src/libwrapper.cpp:446
#: src/libwrapper.cpp:381
#, c-format
msgid "Nothing similar to %s, sorry :(\n"
msgstr "对不起，没有发现和 %s 相似的 :(\n"
#: ../src/sdcv.cpp:89
#, fuzzy
msgid "display version information and exit"
msgstr "-v, --version 显示版本信息并退出\n"
#: ../src/sdcv.cpp:91
#, fuzzy
msgid "display list of available dictionaries and exit"
msgstr "-l, --list-dicts 显示可用的字典列表并退出\n"
#: ../src/sdcv.cpp:93
#, fuzzy
msgid "for search use only dictionary with this bookname"
msgstr "-u, --use-dict 字典名 只使用指定的字典进行单词搜索\n"
#: ../src/sdcv.cpp:94
msgid "bookname"
msgstr ""
#: ../src/sdcv.cpp:96
msgid "for use in scripts"
msgstr ""
#: ../src/sdcv.cpp:98
msgid "print the result formatted as JSON"
msgstr ""
#: ../src/sdcv.cpp:100
msgid "do not fuzzy-search for similar words, only return exact matches"
msgstr ""
#: ../src/sdcv.cpp:102
#, fuzzy
msgid "output must be in utf8"
msgstr "--utf8-output 输出必须是 UTF-8\n"
#: ../src/sdcv.cpp:104
#, fuzzy
msgid "input of sdcv in utf8"
msgstr "--utf8-input sdcv 的输入为 UTF-8\n"
#: ../src/sdcv.cpp:106
#, fuzzy
msgid "use this directory as path to stardict data directory"
msgstr "--data-dir 目录路径 指定 Stardict 数据所在目录的路径\n"
#: ../src/sdcv.cpp:107
msgid "path/to/dir"
msgstr ""
#: ../src/sdcv.cpp:109
msgid ""
"only use the dictionaries in data-dir, do not search in user and system "
"directories"
msgstr ""
#: ../src/sdcv.cpp:111
msgid "colorize the output"
msgstr ""
#: ../src/sdcv.cpp:116
msgid " words"
msgstr ""
#: ../src/sdcv.cpp:122
#, c-format
msgid "Invalid command line arguments: %s\n"
msgstr ""
#: ../src/sdcv.cpp:128
#, c-format
msgid "Console version of Stardict, version %s\n"
msgstr "Stardict 的控制台版本，版本为 %s\n"
#: ../src/sdcv.cpp:206
#, c-format
msgid "g_mkdir failed: %s\n"
msgstr ""
#: ../src/sdcv.cpp:222
msgid "Enter word or phrase: "
msgstr "请输入单词或短语："
#: ../src/sdcv.cpp:230
#, c-format
msgid "There are no words/phrases to translate.\n"
msgstr "没有供翻译的单词或短语。\n"
#: ../src/sdcv.cpp:242
#, fuzzy, c-format
msgid "Dictionary's name Word count\n"
msgstr "字典名 单词量\n"
#: ../src/utils.cpp:48
#: src/utils.cpp:45
#, c-format
msgid "Can not convert %s to current locale.\n"
msgstr "无法将 %s 转换为当前 Locale。\n"

194
po/zh_TW.po
View File

@@ -8,158 +8,122 @@ msgid ""
msgstr ""
"Project-Id-Version: sdcv 0.4.2\n"
"Report-Msgid-Bugs-To: dushistov@mail.ru\n"
"POT-Creation-Date: 2020-08-14 12:58+0300\n"
"POT-Creation-Date: 2006-04-24 15:18+0400\n"
"PO-Revision-Date: 2013-06-12 14:11+0800\n"
"Last-Translator: Wei-Lun Chao <bluebat@member.fsf.org>\n"
"Language-Team: Chinese (traditional) <zh-l10n@linux.org.tw>\n"
"Language: zh_TW\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=UTF-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Plural-Forms: nplurals=1; plural=0;\n"
#: ../src/libwrapper.cpp:300
msgid "popen failed"
msgstr "popen 失敗"
#: ../src/libwrapper.cpp:341
#: src/sdcv.cpp:127
#, c-format
msgid "Can not convert %s to utf8.\n"
msgstr "無法將 %s 轉換為 UTF-8。\n"
#: ../src/libwrapper.cpp:399 ../src/libwrapper.cpp:433
#, fuzzy, c-format
msgid "Found %zu items, similar to %s.\n"
msgstr "找到 %d 項紀錄和 %s 相似。\n"
#: ../src/libwrapper.cpp:417
msgid "Your choice[-1 to abort]: "
msgstr "您的選擇是[-1 表示放棄]："
#: ../src/libwrapper.cpp:427
#, fuzzy, c-format
msgid ""
"Invalid choice.\n"
"It must be from 0 to %zu or -1.\n"
"Unknown option.\n"
"Try '%s --help' for more information.\n"
msgstr ""
"無效的選擇。\n"
"必須是 0 到 %d 之間或 -1。\n"
"不明選項。\n"
"更多資訊請看 '%s --help'。\n"
#: ../src/libwrapper.cpp:446
#: src/sdcv.cpp:134
#, c-format
msgid "Nothing similar to %s, sorry :(\n"
msgstr "抱歉，沒有和 %s 相似者 :(\n"
msgid "Usage: %s [OPTIONS] words\n"
msgstr "用法：%s [選項] 單字…\n"
#: ../src/sdcv.cpp:89
#, fuzzy
msgid "display version information and exit"
#: src/sdcv.cpp:135
#, c-format
msgid "-h, --help display this help and exit\n"
msgstr "-h, --help 顯示本輔助並離開\n"
#: src/sdcv.cpp:136
#, c-format
msgid "-v, --version display version information and exit\n"
msgstr "-v, --version 顯示版本資訊並離開\n"
#: ../src/sdcv.cpp:91
#, fuzzy
msgid "display list of available dictionaries and exit"
#: src/sdcv.cpp:137
#, c-format
msgid "-l, --list-dicts display list of available dictionaries and exit\n"
msgstr "-l, --list-dicts 顯示可用的字典清單並離開\n"
#: ../src/sdcv.cpp:93
#, fuzzy
msgid "for search use only dictionary with this bookname"
#: src/sdcv.cpp:138
#, c-format
msgid "-u, --use-dict bookname for search use only dictionary with this bookname\n"
msgstr "-u, --use-dict 字典名 只使用指定的字典進行單字搜尋\n"
#: ../src/sdcv.cpp:94
msgid "bookname"
msgstr ""
#: src/sdcv.cpp:139
#, c-format
msgid "-n, --non-interactive for use in scripts\n"
msgstr "-n, --non-interactive 在指令稿中使用\n"
#: ../src/sdcv.cpp:96
msgid "for use in scripts"
msgstr ""
#: ../src/sdcv.cpp:98
msgid "print the result formatted as JSON"
msgstr ""
#: ../src/sdcv.cpp:100
msgid "do not fuzzy-search for similar words, only return exact matches"
msgstr ""
#: ../src/sdcv.cpp:102
#, fuzzy
msgid "output must be in utf8"
#: src/sdcv.cpp:140
#, c-format
msgid "--utf8-output output must be in utf8\n"
msgstr "--utf8-output 輸出必須是 UTF-8\n"
#: ../src/sdcv.cpp:104
#, fuzzy
msgid "input of sdcv in utf8"
#: src/sdcv.cpp:141
#, c-format
msgid "--utf8-input input of sdcv in utf8\n"
msgstr "--utf8-input sdcv 的輸入為 UTF-8\n"
#: ../src/sdcv.cpp:106
#, fuzzy
msgid "use this directory as path to stardict data directory"
#: src/sdcv.cpp:142
#, c-format
msgid "--data-dir path/to/dir use this directory as path to stardict data directory\n"
msgstr "--data-dir 目錄路徑 指定 Stardict 資料所在目錄的路徑\n"
#: ../src/sdcv.cpp:107
msgid "path/to/dir"
msgstr ""
#: ../src/sdcv.cpp:109
msgid ""
"only use the dictionaries in data-dir, do not search in user and system "
"directories"
msgstr ""
#: ../src/sdcv.cpp:111
msgid "colorize the output"
msgstr ""
#: ../src/sdcv.cpp:116
msgid " words"
msgstr ""
#: ../src/sdcv.cpp:122
#, c-format
msgid "Invalid command line arguments: %s\n"
msgstr ""
#: ../src/sdcv.cpp:128
#: src/sdcv.cpp:148
#, c-format
msgid "Console version of Stardict, version %s\n"
msgstr "Stardict 的主控臺版本，版本為 %s\n"
#: ../src/sdcv.cpp:206
#, c-format
msgid "g_mkdir failed: %s\n"
msgstr "g_mkdir 失敗：%s\n"
#: ../src/sdcv.cpp:222
msgid "Enter word or phrase: "
msgstr "請輸入單字或片語："
#: ../src/sdcv.cpp:230
#, c-format
msgid "There are no words/phrases to translate.\n"
msgstr "沒有可供翻譯的單字或片語。\n"
#: ../src/sdcv.cpp:242
#: src/sdcv.cpp:169
#, c-format
msgid "Dictionary's name Word count\n"
msgstr "字典名稱 單字數量\n"
#: ../src/utils.cpp:48
#, fuzzy, c-format
msgid "Can not convert %s to current locale.\n"
#: src/sdcv.cpp:191
#, c-format
msgid "g_mkdir failed: %s\n"
msgstr "g_mkdir 失敗：%s\n"
#: src/sdcv.cpp:207
msgid "Enter word or phrase: "
msgstr "請輸入單字或片語："
#: src/sdcv.cpp:215
#, c-format
msgid "There are no words/phrases to translate.\n"
msgstr "沒有可供翻譯的單字或片語。\n"
#: src/libwrapper.cpp:245
msgid "popen failed"
msgstr "popen 失敗"
#: src/libwrapper.cpp:282
#, c-format
msgid "Can not convert %s to utf8.\n"
msgstr "無法將 %s 轉換為 UTF-8。\n"
#~ msgid ""
#~ "Unknown option.\n"
#~ "Try '%s --help' for more information.\n"
#~ msgstr ""
#~ "不明選項。\n"
#~ "更多資訊請看 '%s --help'。\n"
#: src/libwrapper.cpp:339 src/libwrapper.cpp:371
#, c-format
msgid "Found %d items, similar to %s.\n"
msgstr "找到 %d 項紀錄和 %s 相似。\n"
#~ msgid "Usage: %s [OPTIONS] words\n"
#~ msgstr "用法：%s [選項] 單字…\n"
#: src/libwrapper.cpp:352
#, c-format
msgid "Your choice[-1 to abort]: "
msgstr "您的選擇是[-1 表示放棄]："
#~ msgid "-h, --help display this help and exit\n"
#~ msgstr "-h, --help 顯示本輔助並離開\n"
#: src/libwrapper.cpp:366
#, c-format
msgid ""
"Invalid choise.\n"
"It must be from 0 to %d or -1.\n"
msgstr ""
"無效的選擇。\n"
"必須是 0 到 %d 之間或 -1。\n"
#~ msgid "-n, --non-interactive for use in scripts\n"
#~ msgstr "-n, --non-interactive 在指令稿中使用\n"
#: src/libwrapper.cpp:382
#, c-format
msgid "Nothing similar to %s, sorry :(\n"
msgstr "抱歉，沒有和 %s 相似者 :(\n"

116
src/core.rs Normal file
View File

@@ -0,0 +1,116 @@
use ini::Ini;
use std::fs::File;
use std::io::Read;
use std::path::Path;
use std::path::PathBuf;
use std::error::Error;
use index::DictionaryIndex;
use index::MemoryDictionaryIndex;
use index::DiskDictionaryIndex;
use data::DictionaryData;
use data::SimpleDictionaryData;
pub struct Dictionary {
ifo_file_name: PathBuf,
wordcount : usize,
bookname: String,
sametypesequence: String,
index: Box<DictionaryIndex>,
data: Box<DictionaryData>
}
impl Dictionary {
pub fn new(ifo_file_name: &Path) -> Result<Dictionary, String> {
let basename = try!(try!(ifo_file_name.file_stem().ok_or("bad ifo file name")).to_str().ok_or("can not convert file name to unicode"));
let dict_dir = try!(ifo_file_name.parent().ok_or("bad ifo directory name"));
let mut file = try!(File::open(ifo_file_name).map_err(|err| err.to_string()));
let mut ifo_content = String::new();
match file.read_to_string(&mut ifo_content) {
Ok(read_bytes) => { if read_bytes < 3 { return Result::Err("ifo file too small".to_string()) } },
Result::Err(err) => return Result::Err(err.to_string())
};
let content =
if ifo_content.starts_with("\u{feff}") {
&ifo_content[1..]
} else {
&ifo_content[0..]
};
static DICT_MAGIC_DATA: &'static str = "StarDict's dict ifo file";
if !content.starts_with(DICT_MAGIC_DATA) {
return Result::Err("ifo magic not match".to_string());
}
let ifo_cfg = try!(Ini::load_from_str(content).map_err(|err| err.msg));
let section = try!(ifo_cfg.section(None::<String>).ok_or("ifo: parse none section error".to_string()));
let wordcount = try!(section.get("wordcount").ok_or("no wordcount".to_string()));
let wordcount = try!(wordcount.parse::<usize>().map_err(|err| err.description().to_string()));
let idxfilesize = try!(section.get("idxfilesize").ok_or("no idxfilesize".to_string()));
let bookname = try!(section.get("bookname").ok_or("no bookname".to_string()));
let sametypesequence = try!(section.get("sametypesequence").ok_or("no sametypesequence".to_string()));
let idx_path = dict_dir.join(basename.to_string() + ".idx");
let idx_path_gz = dict_dir.join(basename.to_string() + ".idx.gz");
let mut index: Box<DictionaryIndex>;
if idx_path.exists() && idx_path.is_file() {
let disk_dict = try!(DiskDictionaryIndex::new(wordcount, &idx_path));
index = Box::new(disk_dict);
} else if idx_path_gz.exists() && idx_path_gz.is_file() {
let mem_dict = try!(MemoryDictionaryIndex::new_from_gzip(wordcount, &idx_path_gz));
index = Box::new(mem_dict);
} else {
return Result::Err(format!("no index file for {}", ifo_file_name.to_str().unwrap()));
}
let data_path = dict_dir.join(basename.to_string() + ".dict");
let data_path_dz = dict_dir.join(basename.to_string() + ".dict.dz");
let mut data: Box<DictionaryData>;
if data_path.exists() && data_path.is_file() {
let simple_data = try!(SimpleDictionaryData::new(data_path.as_path()));
data = Box::new(simple_data);
} else if data_path_dz.exists() && data_path_dz.is_file() {
return Result::Err("reading dict.dz not implemented".to_string());
} else {
return Result::Err(format!("no data file for {}", ifo_file_name.to_str().unwrap()));
}
Result::Ok(Dictionary{ifo_file_name : ifo_file_name.to_path_buf(), wordcount : wordcount,
bookname : bookname.clone(), sametypesequence: sametypesequence.clone(),
index : index, data: data})
}
pub fn find(&mut self, key: &str) -> Option<String> {
match self.index.find(key) {
Err(idx) => None,
Ok(idx) => {
let key_pos = self.index.get_key(idx);
Some(self.data.get_data(key_pos.1, key_pos.2).unwrap())
}
}
}
}
#[cfg(test)]
mod test {
use super::*;
use std::path::Path;
#[test]
fn open_dict() {
let dic = Dictionary::new(Path::new("tests/stardict-test_dict-2.4.2/test_dict.ifo")).unwrap();
assert_eq!(dic.wordcount, 1_usize);
assert_eq!(dic.bookname, "test_dict");
assert_eq!(dic.sametypesequence, "x");
}
#[test]
fn find_in_dict() {
let mut dic = Dictionary::new(Path::new("tests/stardict-test_dict-2.4.2/test_dict.ifo")).unwrap();
assert_eq!(dic.find("test").unwrap(), "<k>test</k>\ntest passed");
}
}

33
src/data.rs Normal file
View File

@@ -0,0 +1,33 @@
use std::fs::File;
use std::io::Read;
use std::io::Seek;
use std::path::Path;
use std::io::SeekFrom;
use std::str::from_utf8;
pub trait DictionaryData {
fn get_data(& mut self, offset: u64, length: usize) -> Result<String, String>;
}
pub struct SimpleDictionaryData {
data_file: File,
}
impl DictionaryData for SimpleDictionaryData {
fn get_data(& mut self, offset: u64, length: usize) -> Result<String, String> {
try!(self.data_file.seek(SeekFrom::Start(offset)).map_err(|err| err.to_string()));
let mut buffer = Vec::<u8>::with_capacity(length);
buffer.resize(length, 0_u8);
try!(self.data_file.read_exact(& mut buffer).map_err(|err| err.to_string()));
let utf8_s = try!(String::from_utf8(buffer).map_err(|err| "invalid utf-8 data in data".to_string()));
Result::Ok(utf8_s)
}
}
impl SimpleDictionaryData {
pub fn new(data_file_name: &Path) ->Result<SimpleDictionaryData, String> {
let file = try!(File::open(data_file_name).map_err(|err| err.to_string()));
Result::Ok(SimpleDictionaryData{data_file : file})
}
}

729
src/dictziplib.cpp
View File

@@ -21,24 +21,25 @@
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*/
//#define HAVE_MMAP //it will defined in config.h. this can be done by configure.in with a AC_FUNC_MMAP.
#ifdef HAVE_CONFIG_H
#include "config.h"
# include "config.h"
#endif
#include <cassert>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <fcntl.h>
#include <limits.h>
#include <unistd.h>
#include <limits.h>
#include <fcntl.h>
#include <sys/stat.h>
#include "dictziplib.hpp"
#define USE_CACHE 1
@@ -56,424 +57,426 @@
/* For gzip-compatible header, as defined in RFC 1952 */
/* Magic for GZIP (rfc1952) */
#define GZ_MAGIC1 0x1f /* First magic byte */
#define GZ_MAGIC2 0x8b /* Second magic byte */
/* Magic for GZIP (rfc1952) */
#define GZ_MAGIC1 0x1f /* First magic byte */
#define GZ_MAGIC2 0x8b /* Second magic byte */
/* FLaGs (bitmapped), from rfc1952 */
#define GZ_FTEXT 0x01 /* Set for ASCII text */
#define GZ_FHCRC 0x02 /* Header CRC16 */
#define GZ_FEXTRA 0x04 /* Optional field (random access index) */
#define GZ_FNAME 0x08 /* Original name */
#define GZ_COMMENT 0x10 /* Zero-terminated, human-readable comment */
#define GZ_MAX 2 /* Maximum compression */
#define GZ_FAST 4 /* Fasted compression */
/* FLaGs (bitmapped), from rfc1952 */
#define GZ_FTEXT 0x01 /* Set for ASCII text */
#define GZ_FHCRC 0x02 /* Header CRC16 */
#define GZ_FEXTRA 0x04 /* Optional field (random access index) */
#define GZ_FNAME 0x08 /* Original name */
#define GZ_COMMENT 0x10 /* Zero-terminated, human-readable comment */
#define GZ_MAX 2 /* Maximum compression */
#define GZ_FAST 4 /* Fasted compression */
/* These are from rfc1952 */
#define GZ_OS_FAT 0 /* FAT filesystem (MS-DOS, OS/2, NT/Win32) */
#define GZ_OS_AMIGA 1 /* Amiga */
#define GZ_OS_VMS 2 /* VMS (or OpenVMS) */
#define GZ_OS_UNIX 3 /* Unix */
#define GZ_OS_VMCMS 4 /* VM/CMS */
#define GZ_OS_ATARI 5 /* Atari TOS */
#define GZ_OS_HPFS 6 /* HPFS filesystem (OS/2, NT) */
#define GZ_OS_MAC 7 /* Macintosh */
#define GZ_OS_Z 8 /* Z-System */
#define GZ_OS_CPM 9 /* CP/M */
#define GZ_OS_TOPS20 10 /* TOPS-20 */
#define GZ_OS_NTFS 11 /* NTFS filesystem (NT) */
#define GZ_OS_QDOS 12 /* QDOS */
#define GZ_OS_ACORN 13 /* Acorn RISCOS */
#define GZ_OS_UNKNOWN 255 /* unknown */
/* These are from rfc1952 */
#define GZ_OS_FAT 0 /* FAT filesystem (MS-DOS, OS/2, NT/Win32) */
#define GZ_OS_AMIGA 1 /* Amiga */
#define GZ_OS_VMS 2 /* VMS (or OpenVMS) */
#define GZ_OS_UNIX 3 /* Unix */
#define GZ_OS_VMCMS 4 /* VM/CMS */
#define GZ_OS_ATARI 5 /* Atari TOS */
#define GZ_OS_HPFS 6 /* HPFS filesystem (OS/2, NT) */
#define GZ_OS_MAC 7 /* Macintosh */
#define GZ_OS_Z 8 /* Z-System */
#define GZ_OS_CPM 9 /* CP/M */
#define GZ_OS_TOPS20 10 /* TOPS-20 */
#define GZ_OS_NTFS 11 /* NTFS filesystem (NT) */
#define GZ_OS_QDOS 12 /* QDOS */
#define GZ_OS_ACORN 13 /* Acorn RISCOS */
#define GZ_OS_UNKNOWN 255 /* unknown */
#define GZ_RND_S1 'R' /* First magic for random access format */
#define GZ_RND_S2 'A' /* Second magic for random access format */
#define GZ_RND_S1 'R' /* First magic for random access format */
#define GZ_RND_S2 'A' /* Second magic for random access format */
#define GZ_ID1 0 /* GZ_MAGIC1 */
#define GZ_ID2 1 /* GZ_MAGIC2 */
#define GZ_CM 2 /* Compression Method (Z_DEFALTED) */
#define GZ_FLG 3 /* FLaGs (see above) */
#define GZ_MTIME 4 /* Modification TIME */
#define GZ_XFL 8 /* eXtra FLags (GZ_MAX or GZ_FAST) */
#define GZ_OS 9 /* Operating System */
#define GZ_XLEN 10 /* eXtra LENgth (16bit) */
#define GZ_FEXTRA_START 12 /* Start of extra fields */
#define GZ_SI1 12 /* Subfield ID1 */
#define GZ_SI2 13 /* Subfield ID2 */
#define GZ_SUBLEN 14 /* Subfield length (16bit) */
#define GZ_VERSION 16 /* Version for subfield format */
#define GZ_CHUNKLEN 18 /* Chunk length (16bit) */
#define GZ_CHUNKCNT 20 /* Number of chunks (16bit) */
#define GZ_RNDDATA 22 /* Random access data (16bit) */
#define GZ_ID1 0 /* GZ_MAGIC1 */
#define GZ_ID2 1 /* GZ_MAGIC2 */
#define GZ_CM 2 /* Compression Method (Z_DEFALTED) */
#define GZ_FLG 3 /* FLaGs (see above) */
#define GZ_MTIME 4 /* Modification TIME */
#define GZ_XFL 8 /* eXtra FLags (GZ_MAX or GZ_FAST) */
#define GZ_OS 9 /* Operating System */
#define GZ_XLEN 10 /* eXtra LENgth (16bit) */
#define GZ_FEXTRA_START 12 /* Start of extra fields */
#define GZ_SI1 12 /* Subfield ID1 */
#define GZ_SI2 13 /* Subfield ID2 */
#define GZ_SUBLEN 14 /* Subfield length (16bit) */
#define GZ_VERSION 16 /* Version for subfield format */
#define GZ_CHUNKLEN 18 /* Chunk length (16bit) */
#define GZ_CHUNKCNT 20 /* Number of chunks (16bit) */
#define GZ_RNDDATA 22 /* Random access data (16bit) */
#define DICT_UNKNOWN 0
#define DICT_TEXT 1
#define DICT_GZIP 2
#define DICT_DZIP 3
#define DICT_UNKNOWN 0
#define DICT_TEXT 1
#define DICT_GZIP 2
#define DICT_DZIP 3
int DictData::read_header(const std::string &fname, int computeCRC)
{
FILE *str;
int id1, id2, si1, si2;
char buffer[BUFFERSIZE];
int extraLength, subLength;
int i;
char *pt;
int c;
struct stat sb;
unsigned long crc = crc32(0L, Z_NULL, 0);
int count;
unsigned long offset;
FILE *str;
int id1, id2, si1, si2;
char buffer[BUFFERSIZE];
int extraLength, subLength;
int i;
char *pt;
int c;
struct stat sb;
unsigned long crc = crc32( 0L, Z_NULL, 0 );
int count;
unsigned long offset;
if (!(str = fopen(fname.c_str(), "rb"))) {
//err_fatal_errno( __FUNCTION__,
// "Cannot open data file \"%s\" for read\n", filename );
if (!(str = fopen(fname.c_str(), "rb"))) {
//err_fatal_errno( __FUNCTION__,
// "Cannot open data file \"%s\" for read\n", filename );
return -1;
}
}
this->headerLength = GZ_XLEN - 1;
this->type = DICT_UNKNOWN;
this->headerLength = GZ_XLEN - 1;
this->type = DICT_UNKNOWN;
id1 = getc(str);
id2 = getc(str);
id1 = getc( str );
id2 = getc( str );
if (id1 != GZ_MAGIC1 || id2 != GZ_MAGIC2) {
this->type = DICT_TEXT;
fstat(fileno(str), &sb);
this->compressedLength = this->length = sb.st_size;
this->origFilename = fname;
this->mtime = sb.st_mtime;
if (computeCRC) {
rewind(str);
while (!feof(str)) {
if ((count = fread(buffer, 1, BUFFERSIZE, str))) {
crc = crc32(crc, (Bytef *)buffer, count);
}
}
}
this->crc = crc;
fclose(str);
return 0;
}
this->type = DICT_GZIP;
if (id1 != GZ_MAGIC1 || id2 != GZ_MAGIC2) {
this->type = DICT_TEXT;
fstat( fileno( str ), &sb );
this->compressedLength = this->length = sb.st_size;
this->origFilename = fname;
this->mtime = sb.st_mtime;
if (computeCRC) {
rewind( str );
while (!feof( str )) {
if ((count = fread( buffer, 1, BUFFERSIZE, str ))) {
crc = crc32(crc, (Bytef *)buffer, count);
}
}
}
this->crc = crc;
fclose( str );
return 0;
}
this->type = DICT_GZIP;
this->method = getc(str);
this->flags = getc(str);
this->mtime = getc(str) << 0;
this->mtime |= getc(str) << 8;
this->mtime |= getc(str) << 16;
this->mtime |= getc(str) << 24;
this->extraFlags = getc(str);
this->os = getc(str);
this->method = getc( str );
this->flags = getc( str );
this->mtime = getc( str ) << 0;
this->mtime |= getc( str ) << 8;
this->mtime |= getc( str ) << 16;
this->mtime |= getc( str ) << 24;
this->extraFlags = getc( str );
this->os = getc( str );
if (this->flags & GZ_FEXTRA) {
extraLength = getc(str) << 0;
extraLength |= getc(str) << 8;
this->headerLength += extraLength + 2;
si1 = getc(str);
si2 = getc(str);
if (this->flags & GZ_FEXTRA) {
extraLength = getc( str ) << 0;
extraLength |= getc( str ) << 8;
this->headerLength += extraLength + 2;
si1 = getc( str );
si2 = getc( str );
if (si1 == GZ_RND_S1 || si2 == GZ_RND_S2) {
subLength = getc(str) << 0;
subLength |= getc(str) << 8;
this->version = getc(str) << 0;
this->version |= getc(str) << 8;
if (si1 == GZ_RND_S1 || si2 == GZ_RND_S2) {
subLength = getc( str ) << 0;
subLength |= getc( str ) << 8;
this->version = getc( str ) << 0;
this->version |= getc( str ) << 8;
if (this->version != 1) {
//err_internal( __FUNCTION__,
// "dzip header version %d not supported\n",
// this->version );
}
if (this->version != 1) {
//err_internal( __FUNCTION__,
// "dzip header version %d not supported\n",
// this->version );
}
this->chunkLength = getc(str) << 0;
this->chunkLength |= getc(str) << 8;
this->chunkCount = getc(str) << 0;
this->chunkCount |= getc(str) << 8;
this->chunkLength = getc( str ) << 0;
this->chunkLength |= getc( str ) << 8;
this->chunkCount = getc( str ) << 0;
this->chunkCount |= getc( str ) << 8;
if (this->chunkCount <= 0) {
fclose(str);
return 5;
}
this->chunks = (int *)malloc(sizeof(this->chunks[0])
* this->chunkCount);
for (i = 0; i < this->chunkCount; i++) {
this->chunks[i] = getc(str) << 0;
this->chunks[i] |= getc(str) << 8;
}
this->type = DICT_DZIP;
} else {
fseek(str, this->headerLength, SEEK_SET);
}
}
if (this->chunkCount <= 0) {
fclose( str );
return 5;
}
this->chunks = (int *)malloc(sizeof( this->chunks[0] )
* this->chunkCount );
for (i = 0; i < this->chunkCount; i++) {
this->chunks[i] = getc( str ) << 0;
this->chunks[i] |= getc( str ) << 8;
}
this->type = DICT_DZIP;
} else {
fseek( str, this->headerLength, SEEK_SET );
}
}
if (this->flags & GZ_FNAME) { /* FIXME! Add checking against header len */
pt = buffer;
while ((c = getc(str)) && c != EOF)
*pt++ = c;
*pt = '\0';
if (this->flags & GZ_FNAME) { /* FIXME! Add checking against header len */
pt = buffer;
while ((c = getc( str )) && c != EOF)
*pt++ = c;
*pt = '\0';
this->origFilename = buffer;
this->headerLength += this->origFilename.length() + 1;
} else {
this->origFilename = "";
}
this->origFilename = buffer;
this->headerLength += this->origFilename.length() + 1;
} else {
this->origFilename = "";
}
if (this->flags & GZ_COMMENT) { /* FIXME! Add checking for header len */
pt = buffer;
while ((c = getc(str)) && c != EOF)
*pt++ = c;
*pt = '\0';
comment = buffer;
headerLength += comment.length() + 1;
} else {
comment = "";
}
if (this->flags & GZ_COMMENT) { /* FIXME! Add checking for header len */
pt = buffer;
while ((c = getc( str )) && c != EOF)
*pt++ = c;
*pt = '\0';
comment = buffer;
headerLength += comment.length()+1;
} else {
comment = "";
}
if (this->flags & GZ_FHCRC) {
getc(str);
getc(str);
this->headerLength += 2;
}
if (this->flags & GZ_FHCRC) {
getc( str );
getc( str );
this->headerLength += 2;
}
if (ftell(str) != this->headerLength + 1) {
//err_internal( __FUNCTION__,
// "File position (%lu) != header length + 1 (%d)\n",
// ftell( str ), this->headerLength + 1 );
}
if (ftell( str ) != this->headerLength + 1) {
//err_internal( __FUNCTION__,
// "File position (%lu) != header length + 1 (%d)\n",
// ftell( str ), this->headerLength + 1 );
}
fseek(str, -8, SEEK_END);
this->crc = getc(str) << 0;
this->crc |= getc(str) << 8;
this->crc |= getc(str) << 16;
this->crc |= getc(str) << 24;
this->length = getc(str) << 0;
this->length |= getc(str) << 8;
this->length |= getc(str) << 16;
this->length |= getc(str) << 24;
this->compressedLength = ftell(str);
fseek( str, -8, SEEK_END );
this->crc = getc( str ) << 0;
this->crc |= getc( str ) << 8;
this->crc |= getc( str ) << 16;
this->crc |= getc( str ) << 24;
this->length = getc( str ) << 0;
this->length |= getc( str ) << 8;
this->length |= getc( str ) << 16;
this->length |= getc( str ) << 24;
this->compressedLength = ftell( str );
/* Compute offsets */
this->offsets = (unsigned long *)malloc(sizeof(this->offsets[0])
* this->chunkCount);
for (offset = this->headerLength + 1, i = 0;
i < this->chunkCount;
i++) {
this->offsets[i] = offset;
offset += this->chunks[i];
}
/* Compute offsets */
this->offsets = (unsigned long *)malloc( sizeof( this->offsets[0] )
* this->chunkCount );
for (offset = this->headerLength + 1, i = 0;
i < this->chunkCount;
i++) {
this->offsets[i] = offset;
offset += this->chunks[i];
}
fclose(str);
return 0;
fclose( str );
return 0;
}
bool DictData::open(const std::string &fname, int computeCRC)
bool DictData::open(const std::string& fname, int computeCRC)
{
struct stat sb;
int fd;
struct stat sb;
int fd;
this->initialized = 0;
this->initialized = 0;
if (stat(fname.c_str(), &sb) || !S_ISREG(sb.st_mode)) {
//err_warning( __FUNCTION__,
// "%s is not a regular file -- ignoring\n", fname );
return false;
}
if (stat(fname.c_str(), &sb) || !S_ISREG(sb.st_mode)) {
//err_warning( __FUNCTION__,
// "%s is not a regular file -- ignoring\n", fname );
return false;
}
if (read_header(fname, computeCRC)) {
//err_fatal( __FUNCTION__,
// "\"%s\" not in text or dzip format\n", fname );
return false;
}
if (read_header(fname, computeCRC)) {
//err_fatal( __FUNCTION__,
// "\"%s\" not in text or dzip format\n", fname );
return false;
}
if ((fd = ::open(fname.c_str(), O_RDONLY)) < 0) {
//err_fatal_errno( __FUNCTION__,
// "Cannot open data file \"%s\"\n", fname );
return false;
}
if (fstat(fd, &sb)) {
//err_fatal_errno( __FUNCTION__,
// "Cannot stat data file \"%s\"\n", fname );
return false;
}
if ((fd = ::open(fname.c_str(), O_RDONLY )) < 0) {
//err_fatal_errno( __FUNCTION__,
// "Cannot open data file \"%s\"\n", fname );
return false;
}
if (fstat(fd, &sb)) {
//err_fatal_errno( __FUNCTION__,
// "Cannot stat data file \"%s\"\n", fname );
return false;
}
this->size = sb.st_size;
::close(fd);
if (!mapfile.open(fname.c_str(), size))
return false;
this->size = sb.st_size;
::close(fd);
if (!mapfile.open(fname.c_str(), size))
return false;
this->start = mapfile.begin();
this->end = this->start + this->size;
this->start=mapfile.begin();
this->end = this->start + this->size;
for (size_t j = 0; j < DICT_CACHE_SIZE; j++) {
cache[j].chunk = -1;
cache[j].stamp = -1;
cache[j].inBuffer = nullptr;
cache[j].count = 0;
}
for (size_t j = 0; j < DICT_CACHE_SIZE; j++) {
cache[j].chunk = -1;
cache[j].stamp = -1;
cache[j].inBuffer = nullptr;
cache[j].count = 0;
}
return true;
return true;
}
void DictData::close()
{
if (this->chunks)
free(this->chunks);
if (this->offsets)
free(this->offsets);
if (this->chunks)
free(this->chunks);
if (this->offsets)
free(this->offsets);
if (this->initialized) {
if (inflateEnd(&this->zStream)) {
//err_internal( __FUNCTION__,
// "Cannot shut down inflation engine: %s\n",
// this->zStream.msg );
}
}
if (this->initialized) {
if (inflateEnd( &this->zStream )) {
//err_internal( __FUNCTION__,
// "Cannot shut down inflation engine: %s\n",
// this->zStream.msg );
}
}
for (size_t i = 0; i < DICT_CACHE_SIZE; ++i) {
if (this->cache[i].inBuffer)
free(this->cache[i].inBuffer);
}
for (size_t i = 0; i < DICT_CACHE_SIZE; ++i){
if (this -> cache [i].inBuffer)
free (this -> cache [i].inBuffer);
}
}
void DictData::read(char *buffer, unsigned long start, unsigned long size)
{
char *pt;
unsigned long end;
int count;
char *inBuffer;
char outBuffer[OUT_BUFFER_SIZE];
int firstChunk, lastChunk;
int firstOffset, lastOffset;
int i;
int found, target, lastStamp;
static int stamp = 0;
char *pt;
unsigned long end;
int count;
char *inBuffer;
char outBuffer[OUT_BUFFER_SIZE];
int firstChunk, lastChunk;
int firstOffset, lastOffset;
int i;
int found, target, lastStamp;
static int stamp = 0;
end = start + size;
end = start + size;
//buffer = malloc( size + 1 );
//buffer = malloc( size + 1 );
//PRINTF(DBG_UNZIP,
// ("dict_data_read( %p, %lu, %lu )\n",
//h, start, size ));
//PRINTF(DBG_UNZIP,
// ("dict_data_read( %p, %lu, %lu )\n",
//h, start, size ));
switch (this->type) {
case DICT_GZIP:
//err_fatal( __FUNCTION__,
// "Cannot seek on pure gzip format files.\n"
// "Use plain text (for performance)"
// " or dzip format (for space savings).\n" );
break;
case DICT_TEXT:
memcpy(buffer, this->start + start, size);
//buffer[size] = '\0';
break;
case DICT_DZIP:
if (!this->initialized) {
++this->initialized;
this->zStream.zalloc = nullptr;
this->zStream.zfree = nullptr;
this->zStream.opaque = nullptr;
this->zStream.next_in = 0;
this->zStream.avail_in = 0;
this->zStream.next_out = nullptr;
this->zStream.avail_out = 0;
if (inflateInit2(&this->zStream, -15) != Z_OK) {
//err_internal( __FUNCTION__,
// "Cannot initialize inflation engine: %s\n",
//this->zStream.msg );
}
}
firstChunk = start / this->chunkLength;
firstOffset = start - firstChunk * this->chunkLength;
lastChunk = end / this->chunkLength;
lastOffset = end - lastChunk * this->chunkLength;
//PRINTF(DBG_UNZIP,
// (" start = %lu, end = %lu\n"
//"firstChunk = %d, firstOffset = %d,"
//" lastChunk = %d, lastOffset = %d\n",
//start, end, firstChunk, firstOffset, lastChunk, lastOffset ));
for (pt = buffer, i = firstChunk; i <= lastChunk; i++) {
/* Access cache */
found = 0;
target = 0;
lastStamp = INT_MAX;
for (size_t j = 0; j < DICT_CACHE_SIZE; j++) {
switch (this->type) {
case DICT_GZIP:
//err_fatal( __FUNCTION__,
// "Cannot seek on pure gzip format files.\n"
// "Use plain text (for performance)"
// " or dzip format (for space savings).\n" );
break;
case DICT_TEXT:
memcpy( buffer, this->start + start, size );
//buffer[size] = '\0';
break;
case DICT_DZIP:
if (!this->initialized) {
++this->initialized;
this->zStream.zalloc = nullptr;
this->zStream.zfree = nullptr;
this->zStream.opaque = nullptr;
this->zStream.next_in = 0;
this->zStream.avail_in = 0;
this->zStream.next_out = nullptr;
this->zStream.avail_out = 0;
if (inflateInit2( &this->zStream, -15 ) != Z_OK) {
//err_internal( __FUNCTION__,
// "Cannot initialize inflation engine: %s\n",
//this->zStream.msg );
}
}
firstChunk = start / this->chunkLength;
firstOffset = start - firstChunk * this->chunkLength;
lastChunk = end / this->chunkLength;
lastOffset = end - lastChunk * this->chunkLength;
//PRINTF(DBG_UNZIP,
// (" start = %lu, end = %lu\n"
//"firstChunk = %d, firstOffset = %d,"
//" lastChunk = %d, lastOffset = %d\n",
//start, end, firstChunk, firstOffset, lastChunk, lastOffset ));
for (pt = buffer, i = firstChunk; i <= lastChunk; i++) {
/* Access cache */
found = 0;
target = 0;
lastStamp = INT_MAX;
for (size_t j = 0; j < DICT_CACHE_SIZE; j++) {
#if USE_CACHE
if (this->cache[j].chunk == i) {
found = 1;
target = j;
break;
}
if (this->cache[j].chunk == i) {
found = 1;
target = j;
break;
}
#endif
if (this->cache[j].stamp < lastStamp) {
lastStamp = this->cache[j].stamp;
target = j;
}
}
if (this->cache[j].stamp < lastStamp) {
lastStamp = this->cache[j].stamp;
target = j;
}
}
this->cache[target].stamp = ++stamp;
if (found) {
count = this->cache[target].count;
inBuffer = this->cache[target].inBuffer;
} else {
this->cache[target].chunk = i;
if (!this->cache[target].inBuffer)
this->cache[target].inBuffer = (char *)malloc(IN_BUFFER_SIZE);
inBuffer = this->cache[target].inBuffer;
this->cache[target].stamp = ++stamp;
if (found) {
count = this->cache[target].count;
inBuffer = this->cache[target].inBuffer;
} else {
this->cache[target].chunk = i;
if (!this->cache[target].inBuffer)
this->cache[target].inBuffer = (char *)malloc( IN_BUFFER_SIZE );
inBuffer = this->cache[target].inBuffer;
if (this->chunks[i] >= OUT_BUFFER_SIZE) {
//err_internal( __FUNCTION__,
// "this->chunks[%d] = %d >= %ld (OUT_BUFFER_SIZE)\n",
// i, this->chunks[i], OUT_BUFFER_SIZE );
}
memcpy(outBuffer, this->start + this->offsets[i], this->chunks[i]);
if (this->chunks[i] >= OUT_BUFFER_SIZE ) {
//err_internal( __FUNCTION__,
// "this->chunks[%d] = %d >= %ld (OUT_BUFFER_SIZE)\n",
// i, this->chunks[i], OUT_BUFFER_SIZE );
}
memcpy( outBuffer, this->start + this->offsets[i], this->chunks[i] );
this->zStream.next_in = (Bytef *)outBuffer;
this->zStream.avail_in = this->chunks[i];
this->zStream.next_out = (Bytef *)inBuffer;
this->zStream.avail_out = IN_BUFFER_SIZE;
if (inflate(&this->zStream, Z_PARTIAL_FLUSH) != Z_OK) {
//err_fatal( __FUNCTION__, "inflate: %s\n", this->zStream.msg );
}
if (this->zStream.avail_in) {
//err_internal( __FUNCTION__,
// "inflate did not flush (%d pending, %d avail)\n",
// this->zStream.avail_in, this->zStream.avail_out );
}
this->zStream.next_in = (Bytef *)outBuffer;
this->zStream.avail_in = this->chunks[i];
this->zStream.next_out = (Bytef *)inBuffer;
this->zStream.avail_out = IN_BUFFER_SIZE;
if (inflate( &this->zStream, Z_PARTIAL_FLUSH ) != Z_OK) {
//err_fatal( __FUNCTION__, "inflate: %s\n", this->zStream.msg );
}
if (this->zStream.avail_in) {
//err_internal( __FUNCTION__,
// "inflate did not flush (%d pending, %d avail)\n",
// this->zStream.avail_in, this->zStream.avail_out );
}
count = IN_BUFFER_SIZE - this->zStream.avail_out;
count = IN_BUFFER_SIZE - this->zStream.avail_out;
this->cache[target].count = count;
}
this->cache[target].count = count;
}
if (i == firstChunk) {
if (i == lastChunk) {
memcpy(pt, inBuffer + firstOffset, lastOffset - firstOffset);
pt += lastOffset - firstOffset;
} else {
if (count != this->chunkLength) {
//err_internal( __FUNCTION__,
// "Length = %d instead of %d\n",
//count, this->chunkLength );
}
memcpy(pt, inBuffer + firstOffset,
this->chunkLength - firstOffset);
pt += this->chunkLength - firstOffset;
}
} else if (i == lastChunk) {
memcpy(pt, inBuffer, lastOffset);
pt += lastOffset;
} else {
assert(count == this->chunkLength);
memcpy(pt, inBuffer, this->chunkLength);
pt += this->chunkLength;
}
}
//*pt = '\0';
break;
case DICT_UNKNOWN:
//err_fatal( __FUNCTION__, "Cannot read unknown file type\n" );
break;
}
if (i == firstChunk) {
if (i == lastChunk) {
memcpy( pt, inBuffer + firstOffset, lastOffset-firstOffset);
pt += lastOffset - firstOffset;
} else {
if (count != this->chunkLength ) {
//err_internal( __FUNCTION__,
// "Length = %d instead of %d\n",
//count, this->chunkLength );
}
memcpy( pt, inBuffer + firstOffset,
this->chunkLength - firstOffset );
pt += this->chunkLength - firstOffset;
}
} else if (i == lastChunk) {
memcpy( pt, inBuffer, lastOffset );
pt += lastOffset;
} else {
assert( count == this->chunkLength );
memcpy( pt, inBuffer, this->chunkLength );
pt += this->chunkLength;
}
}
//*pt = '\0';
break;
case DICT_UNKNOWN:
//err_fatal( __FUNCTION__, "Cannot read unknown file type\n" );
break;
}
}

79
src/dictziplib.hpp
View File

@@ -7,50 +7,49 @@
#include "mapfile.hpp"
struct DictCache {
int chunk;
char *inBuffer;
int stamp;
int count;
int chunk;
char *inBuffer;
int stamp;
int count;
};
class DictData
{
class DictData {
public:
static const size_t DICT_CACHE_SIZE = 5;
DictData() {}
~DictData() { close(); }
bool open(const std::string &filename, int computeCRC);
void close();
void read(char *buffer, unsigned long start, unsigned long size);
static const size_t DICT_CACHE_SIZE = 5;
DictData() {}
~DictData() { close(); }
bool open(const std::string& filename, int computeCRC);
void close();
void read(char *buffer, unsigned long start, unsigned long size);
private:
const char *start; /* start of mmap'd area */
const char *end; /* end of mmap'd area */
unsigned long size; /* size of mmap */
const char *start; /* start of mmap'd area */
const char *end; /* end of mmap'd area */
unsigned long size; /* size of mmap */
int type;
z_stream zStream;
int initialized;
int headerLength;
int method;
int flags;
time_t mtime;
int extraFlags;
int os;
int version;
int chunkLength;
int chunkCount;
int *chunks;
unsigned long *offsets; /* Sum-scan of chunks. */
std::string origFilename;
std::string comment;
unsigned long crc;
unsigned long length;
unsigned long compressedLength;
DictCache cache[DICT_CACHE_SIZE];
MapFile mapfile;
int type;
z_stream zStream;
int initialized;
int headerLength;
int method;
int flags;
time_t mtime;
int extraFlags;
int os;
int version;
int chunkLength;
int chunkCount;
int *chunks;
unsigned long *offsets; /* Sum-scan of chunks. */
std::string origFilename;
std::string comment;
unsigned long crc;
unsigned long length;
unsigned long compressedLength;
DictCache cache[DICT_CACHE_SIZE];
MapFile mapfile;
int read_header(const std::string &filename, int computeCRC);
int read_header(const std::string &filename, int computeCRC);
};

105
src/distance.cpp
View File

@@ -33,6 +33,7 @@ The Levenshtein distance algorithm has been used in:
* Plagiarism detection
*/
#include <cstdlib>
#include <cstring>
@@ -55,39 +56,43 @@ Enhanced Dynamic Programming ASM Algorithm"
static inline int minimum(const int a, const int b, const int c)
{
int min = a;
if (b < min)
if ( b < min )
min = b;
if (c < min)
if ( c < min )
min = c;
return min;
}
int EditDistance::CalEditDistance(const gunichar *s, const gunichar *t, const int limit)
int EditDistance::CalEditDistance(const gunichar *s,const gunichar *t,const int limit)
/*Compute levenshtein distance between s and t, this is using QUICK algorithm*/
{
int n = 0, m = 0, iLenDif, k, i, j, cost;
int n=0,m=0,iLenDif,k,i,j,cost;
// Remove leftmost matching portion of strings
while (*s && (*s == *t)) {
while ( *s && (*s==*t) )
{
s++;
t++;
}
while (s[n]) {
n++;
}
while (t[m]) {
m++;
t++;
}
while (s[n])
{
n++;
}
while (t[m])
{
m++;
}
// Remove rightmost matching portion of strings by decrement n and m.
while (n && m && (*(s + n - 1) == *(t + m - 1))) {
n--;
m--;
while ( n && m && (*(s+n-1)==*(t+m-1)) )
{
n--;m--;
}
if (m == 0 || n == 0 || d == nullptr)
return (m + n);
if (m < n) {
const gunichar *temp = s;
if ( m==0 || n==0 || d==nullptr )
return (m+n);
if ( m < n )
{
const gunichar * temp = s;
int itemp = n;
s = t;
t = temp;
@@ -95,51 +100,55 @@ int EditDistance::CalEditDistance(const gunichar *s, const gunichar *t, const in
m = itemp;
}
iLenDif = m - n;
if (iLenDif >= limit)
if ( iLenDif >= limit )
return iLenDif;
// step 1
n++;
m++;
// d=(int*)malloc(sizeof(int)*m*n);
if (m * n > currentelements) {
currentelements = m * n * 2; // double the request
d = static_cast<int *>(realloc(d, sizeof(int) * currentelements));
if (nullptr == d)
return (m + n);
n++;m++;
// d=(int*)malloc(sizeof(int)*m*n);
if ( m*n > currentelements )
{
currentelements = m*n*2; // double the request
d = static_cast<int*>(realloc(d, sizeof(int) * currentelements));
if ( nullptr == d )
return (m+n);
}
// step 2, init matrix
for (k = 0; k < n; k++)
for (k=0;k<n;k++)
d[k] = k;
for (k = 1; k < m; k++)
d[k * n] = k;
for (k=1;k<m;k++)
d[k*n] = k;
// step 3
for (i = 1; i < n; i++) {
for (i=1;i<n;i++)
{
// first calculate column, d(i,j)
for (j = 1; j < iLenDif + i; j++) {
cost = s[i - 1] == t[j - 1] ? 0 : 1;
d[j * n + i] = minimum(d[(j - 1) * n + i] + 1, d[j * n + i - 1] + 1, d[(j - 1) * n + i - 1] + cost);
for ( j=1;j<iLenDif+i;j++ )
{
cost = s[i-1]==t[j-1]?0:1;
d[j*n+i] = minimum(d[(j-1)*n+i]+1,d[j*n+i-1]+1,d[(j-1)*n+i-1]+cost);
#ifdef COVER_TRANSPOSITION
if (i >= 2 && j >= 2 && (d[j * n + i] - d[(j - 2) * n + i - 2] == 2)
&& (s[i - 2] == t[j - 1]) && (s[i - 1] == t[j - 2]))
d[j * n + i]--;
if ( i>=2 && j>=2 && (d[j*n+i]-d[(j-2)*n+i-2]==2)
&& (s[i-2]==t[j-1]) && (s[i-1]==t[j-2]) )
d[j*n+i]--;
#endif
}
// second calculate row, d(k,j)
// now j==iLenDif+i;
for (k = 1; k <= i; k++) {
cost = s[k - 1] == t[j - 1] ? 0 : 1;
d[j * n + k] = minimum(d[(j - 1) * n + k] + 1, d[j * n + k - 1] + 1, d[(j - 1) * n + k - 1] + cost);
for ( k=1;k<=i;k++ )
{
cost = s[k-1]==t[j-1]?0:1;
d[j*n+k] = minimum(d[(j-1)*n+k]+1,d[j*n+k-1]+1,d[(j-1)*n+k-1]+cost);
#ifdef COVER_TRANSPOSITION
if (k >= 2 && j >= 2 && (d[j * n + k] - d[(j - 2) * n + k - 2] == 2)
&& (s[k - 2] == t[j - 1]) && (s[k - 1] == t[j - 2]))
d[j * n + k]--;
if ( k>=2 && j>=2 && (d[j*n+k]-d[(j-2)*n+k-2]==2)
&& (s[k-2]==t[j-1]) && (s[k-1]==t[j-2]) )
d[j*n+k]--;
#endif
}
// test if d(i,j) limit gets equal or exceed
if (d[j * n + i] >= limit) {
return d[j * n + i];
if ( d[j*n+i] >= limit )
{
return d[j*n+i];
}
}
// d(n-1,m-1)
return d[n * m - 1];
return d[n*m-1];
}

19
src/distance.hpp
View File

@@ -3,24 +3,21 @@
#include <cstdlib>
#include <glib.h>
class EditDistance
{
class EditDistance {
public:
EditDistance()
{
EditDistance() {
currentelements = 2500; // It's enough for most conditions :-)
d = static_cast<int *>(malloc(sizeof(int) * currentelements));
d = static_cast<int *>(malloc(sizeof(int)*currentelements));
}
~EditDistance()
{
~EditDistance() {
if (d != nullptr)
free(d);
}
EditDistance(const EditDistance &) = delete;
EditDistance &operator=(const EditDistance &) = delete;
int CalEditDistance(const gunichar *s, const gunichar *t, const int limit);
EditDistance(const EditDistance&) = delete;
EditDistance& operator=(const EditDistance&) = delete;
int CalEditDistance( const gunichar *s, const gunichar *t, const int limit );
private:
int *d;
int currentelements;
};

308
src/index.rs Normal file
View File

@@ -0,0 +1,308 @@
use std::str::from_utf8;
use std::cmp::Ordering;
use std::io::Cursor;
use byteorder::{NetworkEndian, ReadBytesExt};
use mem_mapped_file::MemMappedFile;
use std::path::Path;
use std::fs::File;
use std::io::Read;
use flate2::read::GzDecoder;
use std::error::Error;
pub trait DictionaryIndex {
fn get_key(&self, idx: usize) -> (&str, u64, usize);
fn count(&self) -> usize;
fn find(&self, key: &str) -> Result<usize, usize>;
}
pub struct MemoryDictionaryIndex {
idx_content: Vec<u8>,
wordlist: Vec<usize>,
}
fn g_ascii_strcasecmp(s1: &str, s2: &str) -> isize {
fn is_upper(c: u8) -> bool { c >= b'A' && c <= b'Z' }
fn to_lower(c: u8) -> u8 { if is_upper(c) { c - b'A' + b'a' } else { c } }
let mut it1 = s1.bytes();
let mut it2 = s2.bytes();
loop {
match (it1.next(), it2.next()) {
(None, None) => return 0,
(Some(b1), None) => return b1 as isize,
(None, Some(b2)) => return -(b2 as isize),
(Some(b1), Some(b2)) => {
let c1 = to_lower(b1) as isize;
let c2 = to_lower(b2) as isize;
if c1 != c2 {
return c1 - c2;
}
},
}
}
0_isize
}
fn stardict_strcmp(s1: &str, s2: &str) -> isize {
/*
#define ISUPPER(c) ((c) >= 'A' && (c) <= 'Z')
#define TOLOWER(c) (ISUPPER (c) ? (c) - 'A' + 'a' : (c))
gint
g_ascii_strcasecmp (const gchar *s1,
const gchar *s2)
{
gint c1, c2;
g_return_val_if_fail (s1 != NULL, 0);
g_return_val_if_fail (s2 != NULL, 0);
while (*s1 && *s2)
{
c1 = (gint)(guchar) TOLOWER (*s1);
c2 = (gint)(guchar) TOLOWER (*s2);
if (c1 != c2)
return (c1 - c2);
s1++; s2++;
}
return (((gint)(guchar) *s1) - ((gint)(guchar) *s2));
}
const gint a = g_ascii_strcasecmp(s1, s2);
if (a == 0)
return strcmp(s1, s2);
else
return a;
*/
let res = g_ascii_strcasecmp(s1, s2);
if res == 0 {
assert_eq!(s1.len(), s2.len());
for it in s1.bytes().zip(s2.bytes()) {
let (b1, b2) = it;
if b1 != b2 {
return (b1 as isize) - (b2 as isize);
}
}
0_isize
} else {
res
}
}
fn stardict_str_order(s1: &str, s2: &str) -> Ordering {
let cmp_res = stardict_strcmp(s1, s2);
if cmp_res < 0 {
Ordering::Less
} else if cmp_res > 0 {
Ordering::Greater
} else {
Ordering::Equal
}
}
fn get_key_by_offset(content: &[u8], key_pos: usize) -> (&str, u64, usize) {
let key = &content[key_pos..];
let end_of_key = key.iter().position(|&x| x == b'\0').unwrap() + key_pos;
let mut reader = Cursor::new(&content[end_of_key + 1..]);
let offset = reader.read_u32::<NetworkEndian>().unwrap() as u64;
let length = reader.read_u32::<NetworkEndian>().unwrap() as usize;
(from_utf8(&content[key_pos..end_of_key]).unwrap(), offset, length)
}
impl DictionaryIndex for MemoryDictionaryIndex {
fn get_key(&self, idx: usize) -> (&str, u64, usize) {
let key_pos = self.wordlist[idx];
get_key_by_offset(&self.idx_content, key_pos)
/*
let key = &self.idx_content[key_pos..];
let end_of_key = key.iter().position(|&x| x == b'\0').unwrap();
let mut reader = Cursor::new(&self.idx_content[end_of_key + 1..]);
let offset = reader.read_u32::<NetworkEndian>().unwrap() as u64;
let length = reader.read_u32::<NetworkEndian>().unwrap() as usize;
(from_utf8(&self.idx_content[key_pos..(key_pos + end_of_key)]).unwrap(), offset, length)*/
}
fn count(&self) -> usize {
self.wordlist.len()
}
fn find(&self, key: &str) -> Result<usize, usize> {
self.wordlist.binary_search_by(
|probe| stardict_str_order(get_key_by_offset(&self.idx_content, *probe).0, key)
)
}
}
fn get_offsets_of_phrases_in_index(expected_wordcount: usize, idx_content: &[u8]) -> Result<Vec<usize>, String> {
const PADDING_LENGTH: usize = 8;
let mut wordlist = vec![];
wordlist.reserve(expected_wordcount);
{
let mut slice = idx_content;
let mut pos : usize = 0;
while let Some(idx) = slice.iter().position(|&x| x == b'\0') {
let (head, tail) = slice.split_at(idx);
try!(from_utf8(head).map_err(|err| "invalid utf-8 in key".to_string()));
wordlist.push(pos);
pos += head.len() + PADDING_LENGTH + 1;
// +1 to skip over the NUL
if tail.len() > PADDING_LENGTH + 1 {
slice = &tail[PADDING_LENGTH + 1..];
} else {
break;
}
}
}
if wordlist.len() != expected_wordcount {
Result::Err(format!("Expect words in index {}, got {} words", expected_wordcount, wordlist.len()))
} else {
Result::Ok(wordlist)
}
}
impl MemoryDictionaryIndex {
pub fn new_from_vec(expected_wordcount: usize, idx_content: Vec<u8>) -> Result<MemoryDictionaryIndex, String> {
let wordlist = try!(get_offsets_of_phrases_in_index(expected_wordcount, idx_content.as_slice()));
Result::Ok(MemoryDictionaryIndex {idx_content: idx_content, wordlist: wordlist})
}
pub fn new_from_gzip(expected_wordcount: usize, idx_gz_file_path: &Path) -> Result<MemoryDictionaryIndex, String> {
let mut idx_file = try!(File::open(idx_gz_file_path).map_err(|err| err.description().to_string()));
let mut gzip_decoder = try!(GzDecoder::new(idx_file).map_err(|err| err.description().to_string()));
let mut idx_content = Vec::<u8>::new();
if let Result::Err(err) = gzip_decoder.read_to_end(&mut idx_content) {
return Result::Err(format!("Can not read index file: {}", err.description()));
}
let wordlist = try!(get_offsets_of_phrases_in_index(expected_wordcount, idx_content.as_slice()));
Result::Ok(MemoryDictionaryIndex {idx_content: idx_content, wordlist: wordlist})
}
}
pub struct DiskDictionaryIndex {
file_map: MemMappedFile,
wordlist: Vec<usize>,
}
impl DictionaryIndex for DiskDictionaryIndex {
fn get_key(&self, idx: usize) -> (&str, u64, usize) {
let key_pos = self.wordlist[idx];
let idx_content = self.file_map.get_chunk(0, self.file_map.len()).unwrap();
get_key_by_offset(idx_content, key_pos)
}
fn count(&self) -> usize { self.wordlist.len() }
fn find(&self, key: &str) -> Result<usize, usize> {
let idx_content = self.file_map.get_chunk(0, self.file_map.len()).unwrap();
self.wordlist.binary_search_by(
|probe| stardict_str_order(get_key_by_offset(idx_content, *probe).0, key)
)
}
}
impl DiskDictionaryIndex {
pub fn new(expected_wordcount: usize, idx_file_path: &Path) -> Result<DiskDictionaryIndex, String> {
let file_map = try!(MemMappedFile::new(idx_file_path));
let whole_map = try!(file_map.get_chunk(0, file_map.len()));
let wordlist = try!(get_offsets_of_phrases_in_index(expected_wordcount, whole_map));
Ok(DiskDictionaryIndex{file_map: file_map, wordlist: wordlist})
}
}
#[cfg(test)]
mod test {
use super::*;
use super::stardict_str_order;
use super::stardict_strcmp;
use std::path::Path;
use std::fs::File;
use std::io::Read;
use std::io::BufReader;
use std::io::BufRead;
use std::collections::HashSet;
#[test]
fn index_memory_open() {
let idx_file_name = Path::new("tests/stardict-test_dict-2.4.2/test_dict.idx");
let mut file = File::open(idx_file_name).unwrap();
let mut idx_content = Vec::<u8>::new();
file.read_to_end(&mut idx_content).unwrap();
let mut index = MemoryDictionaryIndex::new_from_vec(1, idx_content).unwrap();
assert_eq!(1_usize, index.count());
assert_eq!("test", index.get_key(0).0);
let idx_file_name = Path::new("tests/words_dic/stardict-words-2.4.2/words.idx");
let mut file = File::open(idx_file_name).unwrap();
let mut idx_content = Vec::<u8>::new();
file.read_to_end(&mut idx_content).unwrap();
let index_size = 1671704_usize;
let mut mem_index = MemoryDictionaryIndex::new_from_vec(index_size, idx_content).unwrap();
assert_eq!(index_size, mem_index.count());
let mut disk_index = DiskDictionaryIndex::new(index_size, idx_file_name).unwrap();
assert_eq!(index_size, disk_index.count());
let mut gz_mem_index = MemoryDictionaryIndex::new_from_gzip(index_size,
Path::new("tests/words_dic/stardict-words-2.4.2/words.idx.gz")).unwrap();
assert_eq!(index_size, gz_mem_index.count());
{
let mut counter: usize = 0;
let f = File::open("tests/words_dic/words.dummy").unwrap();
let mut file = BufReader::new(&f);
let mut dic_words = HashSet::new();
for line in file.lines() {
let l = line.unwrap();
dic_words.insert(l);
}
for i in 0..index.count() {
for index in [&mem_index as &DictionaryIndex, &disk_index as &DictionaryIndex, &gz_mem_index as &DictionaryIndex].iter() {
let (key, _, _) = index.get_key(i);
if !dic_words.contains(key) {
panic!("no '{}'(len {}) idx {} in dic_words", key, key.len(), i);
}
match index.find(key) {
Err(idx) => panic!("we search '{}', and not found err({})", key, idx),
Ok(idx) => assert_eq!(idx, i),
}
}
}
}
}
#[test]
fn index_stardict_strcmp_small() {
let arr_s = ["a", "b", "c", "d", "z"];
let seek = "c";
assert_eq!(arr_s.binary_search_by(|probe| stardict_str_order(probe, seek)), Ok(2));
let seek = "e";
assert_eq!(arr_s.binary_search_by(|probe| stardict_str_order(probe, seek)), Err(4));
}
#[test]
fn index_stardict_strcmp_big() {
let mut exp_res_list = vec![];
{
let f = File::open("tests/stardict_strcmp_test_data_cmp_exp.txt").unwrap();
let mut file = BufReader::new(&f);
for line in file.lines() {
let line = line.unwrap();
let exp_res = line.parse::<isize>().unwrap();
exp_res_list.push(exp_res);
}
}
let f = File::open("tests/stardict_strcmp_test_data.txt").unwrap();
let mut file = BufReader::new(&f);
let mut prev_line : String = "".to_string();
let mut counter : u8 = 0;
let mut exp_it = exp_res_list.iter();
for line in file.lines() {
if counter == 1 {
let cur_line = line.unwrap();
let res = stardict_strcmp(&prev_line, &cur_line);
let exp_res = exp_it.next().unwrap();
if res != *exp_res {
panic!("we expect {}, got {} for '{}' vs '{}'", exp_res, res, prev_line, cur_line);
}
} else {
prev_line = line.unwrap();
}
counter = (counter + 1) % 2;
}
}
}

630
src/libwrapper.cpp
View File

@@ -15,11 +15,11 @@
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
# include "config.h"
#endif
#include <cstring>
@@ -48,411 +48,373 @@ static const char *ABR_VISFMT = ESC_GREEN;
static std::string xdxf2text(const char *p, bool colorize_output)
{
std::string res;
for (; *p; ++p) {
if (*p != '<') {
if (g_str_has_prefix(p, "&gt;")) {
res += ">";
p += 3;
} else if (g_str_has_prefix(p, "&lt;")) {
res += "<";
p += 3;
} else if (g_str_has_prefix(p, "&amp;")) {
res += "&";
p += 4;
} else if (g_str_has_prefix(p, "&quot;")) {
res += "\"";
p += 5;
} else if (g_str_has_prefix(p, "&apos;")) {
res += "\'";
p += 5;
} else
res += *p;
continue;
}
std::string res;
for (; *p; ++p) {
if (*p != '<') {
if (g_str_has_prefix(p, "&gt;")) {
res += ">";
p += 3;
} else if (g_str_has_prefix(p, "&lt;")) {
res += "<";
p += 3;
} else if (g_str_has_prefix(p, "&amp;")) {
res += "&";
p += 4;
} else if (g_str_has_prefix(p, "&quot;")) {
res += "\"";
p += 5;
} else if (g_str_has_prefix(p, "&apos;")) {
res += "\'";
p += 5;
} else
res += *p;
continue;
}
const char *next = strchr(p, '>');
if (!next)
continue;
const char *next = strchr(p, '>');
if (!next)
continue;
const std::string name(p + 1, next - p - 1);
const std::string name(p+1, next-p-1);
if (name == "abr")
res += colorize_output ? ABR_VISFMT : "";
else if (name == "/abr")
res += colorize_output ? ESC_END : "";
else if (name == "k") {
const char *begin = next;
if ((next = strstr(begin, "</k>")) != nullptr)
next += sizeof("</k>") - 1 - 1;
else
next = begin;
if (name == "abr")
res += colorize_output ? ABR_VISFMT : "";
else if (name=="/abr")
res += colorize_output ? ESC_END : "";
else if (name == "k") {
const char *begin = next;
if ((next = strstr(begin, "</k>")) != nullptr)
next += sizeof("</k>") - 1 - 1;
else
next = begin;
} else if (name == "kref") {
res += colorize_output ? KREF_VISFMT : "";
} else if (name == "/kref") {
res += colorize_output ? ESC_END : "";
} else if (name == "b")
res += colorize_output ? ESC_BOLD : "";
else if (name == "/b")
res += colorize_output ? ESC_END : "";
else if (name == "i")
res += colorize_output ? ESC_ITALIC : "";
else if (name == "/i")
res += colorize_output ? ESC_END : "";
else if (name == "tr") {
} else if (name == "b")
res += colorize_output ? ESC_BOLD : "";
else if (name=="/b")
res += colorize_output ? ESC_END : "";
else if (name == "i")
res += colorize_output ? ESC_ITALIC : "";
else if (name == "/i")
res += colorize_output ? ESC_END : "";
else if (name == "tr") {
if (colorize_output)
res += TRANSCRIPTION_VISFMT;
res += "[";
} else if (name == "/tr") {
res += "]";
res += "[";
} else if (name == "/tr") {
res += "]";
if (colorize_output)
res += ESC_END;
} else if (name == "ex")
res += colorize_output ? EXAMPLE_VISFMT : "";
else if (name == "/ex")
res += colorize_output ? ESC_END : "";
else if (!name.empty() && name[0] == 'c' && name != "co") {
std::string::size_type pos = name.find("code");
if (pos != std::string::npos) {
pos += sizeof("code=\"") - 1;
std::string::size_type end_pos = name.find("\"");
const std::string color(name, pos, end_pos - pos);
res += "";
} else {
res += "";
}
} else if (name == "/c")
res += "";
} else if (name == "ex")
res += colorize_output ? EXAMPLE_VISFMT : "";
else if (name == "/ex")
res += colorize_output ? ESC_END : "";
else if (!name.empty() && name[0] == 'c' && name != "co") {
std::string::size_type pos = name.find("code");
if (pos != std::string::npos) {
pos += sizeof("code=\"") - 1;
std::string::size_type end_pos = name.find("\"");
const std::string color(name, pos, end_pos - pos);
res += "";
} else {
res += "";
}
} else if (name == "/c")
res += "";
p = next;
}
return res;
p = next;
}
return res;
}
static std::string parse_data(const gchar *data, bool colorize_output)
{
if (!data)
return "";
if (!data)
return "";
std::string res;
guint32 data_size, sec_size = 0;
gchar *m_str;
const gchar *p = data;
data_size = get_uint32(p);
p += sizeof(guint32);
while (guint32(p - data) < data_size) {
switch (*p++) {
case 'h': // HTML data
case 'w': // WikiMedia markup data
case 'm': // plain text, utf-8
case 'l': // not utf-8, some other locale encoding, discouraged, need more work...
sec_size = strlen(p);
if (sec_size) {
res += "\n";
m_str = g_strndup(p, sec_size);
res += m_str;
g_free(m_str);
}
sec_size++;
break;
case 'g': // pango markup data
case 'x': // xdxf
sec_size = strlen(p);
if (sec_size) {
res += "\n";
m_str = g_strndup(p, sec_size);
res += xdxf2text(m_str, colorize_output);
g_free(m_str);
}
sec_size++;
break;
case 't': // english phonetic string
sec_size = strlen(p);
if (sec_size) {
res += "\n";
std::string res;
guint32 data_size, sec_size = 0;
gchar *m_str;
const gchar *p = data;
data_size = get_uint32(p);
p += sizeof(guint32);
while (guint32(p - data)<data_size) {
switch (*p++) {
case 'm':
case 'l': //need more work...
sec_size = strlen(p);
if (sec_size) {
res+="\n";
m_str = g_strndup(p, sec_size);
res += m_str;
g_free(m_str);
}
sec_size++;
break;
case 'g':
case 'x':
sec_size = strlen(p);
if (sec_size) {
res+="\n";
m_str = g_strndup(p, sec_size);
res += xdxf2text(m_str, colorize_output);
g_free(m_str);
}
sec_size++;
break;
case 't':
sec_size = strlen(p);
if(sec_size){
res += "\n";
if (colorize_output)
res += TRANSCRIPTION_VISFMT;
res += "[" + std::string(p, sec_size) + "]";
res += "[" + std::string(p, sec_size) + "]";
if (colorize_output)
res += ESC_END;
}
sec_size++;
break;
case 'k': // KingSoft PowerWord data
case 'y': // chinese YinBiao or japanese kana, utf-8
sec_size = strlen(p);
}
sec_size++;
break;
case 'k':
case 'y':
sec_size = strlen(p);
if (sec_size)
res += std::string(p, sec_size);
sec_size++;
break;
case 'W': // wav file
case 'P': // picture data
sec_size = get_uint32(p);
sec_size += sizeof(guint32);
break;
}
p += sec_size;
}
sec_size++;
break;
case 'W':
case 'P':
sec_size = get_uint32(p);
sec_size += sizeof(guint32);
break;
}
p += sec_size;
}
return res;
return res;
}
void Library::SimpleLookup(const std::string &str, TSearchResultList &res_list)
void Library::SimpleLookup(const std::string &str, TSearchResultList& res_list)
{
std::set<glong> wordIdxs;
res_list.reserve(ndicts());
for (gint idict = 0; idict < ndicts(); ++idict) {
wordIdxs.clear();
if (SimpleLookupWord(str.c_str(), wordIdxs, idict))
for (auto &wordIdx : wordIdxs)
res_list.push_back(
TSearchResult(dict_name(idict),
poGetWord(wordIdx, idict),
parse_data(poGetWordData(wordIdx, idict),
colorize_output_)));
}
glong ind;
res_list.reserve(ndicts());
for (gint idict = 0; idict < ndicts(); ++idict)
if (SimpleLookupWord(str.c_str(), ind, idict))
res_list.push_back(
TSearchResult(dict_name(idict),
poGetWord(ind, idict),
parse_data(poGetWordData(ind, idict), colorize_output_)));
}
void Library::LookupWithFuzzy(const std::string &str, TSearchResultList &res_list)
void Library::LookupWithFuzzy(const std::string &str, TSearchResultList& res_list)
{
static const int MAXFUZZY = 10;
static const int MAXFUZZY=10;
gchar *fuzzy_res[MAXFUZZY];
if (!Libs::LookupWithFuzzy(str.c_str(), fuzzy_res, MAXFUZZY))
return;
gchar *fuzzy_res[MAXFUZZY];
if (!Libs::LookupWithFuzzy(str.c_str(), fuzzy_res, MAXFUZZY))
return;
for (gchar **p = fuzzy_res, **end = (fuzzy_res + MAXFUZZY); p != end && *p; ++p) {
SimpleLookup(*p, res_list);
g_free(*p);
}
for (gchar **p = fuzzy_res, **end = (fuzzy_res + MAXFUZZY); p != end && *p; ++p) {
SimpleLookup(*p, res_list);
g_free(*p);
}
}
void Library::LookupWithRule(const std::string &str, TSearchResultList &res_list)
void Library::LookupWithRule(const std::string &str, TSearchResultList& res_list)
{
std::vector<gchar *> match_res((MAX_MATCH_ITEM_PER_LIB)*ndicts());
std::vector<gchar *> match_res((MAX_MATCH_ITEM_PER_LIB) * ndicts());
const gint nfound = Libs::LookupWithRule(str.c_str(), &match_res[0]);
if (nfound == 0)
return;
const gint nfound = Libs::LookupWithRule(str.c_str(), &match_res[0]);
if (nfound == 0)
return;
for (gint i = 0; i < nfound; ++i) {
SimpleLookup(match_res[i], res_list);
g_free(match_res[i]);
}
for (gint i = 0; i < nfound; ++i) {
SimpleLookup(match_res[i], res_list);
g_free(match_res[i]);
}
}
void Library::LookupData(const std::string &str, TSearchResultList &res_list)
void Library::LookupData(const std::string &str, TSearchResultList& res_list)
{
std::vector<std::vector<gchar *>> drl(ndicts());
if (!Libs::LookupData(str.c_str(), &drl[0]))
return;
for (int idict = 0; idict < ndicts(); ++idict)
for (gchar *res : drl[idict]) {
SimpleLookup(res, res_list);
g_free(res);
}
std::vector<std::vector<gchar *> > drl(ndicts());
if (!Libs::LookupData(str.c_str(), &drl[0]))
return;
for (int idict = 0; idict < ndicts(); ++idict)
for (gchar *res : drl[idict]) {
SimpleLookup(res, res_list);
g_free(res);
}
}
void Library::print_search_result(FILE *out, const TSearchResult &res, bool &first_result)
void Library::print_search_result(FILE *out, const TSearchResult & res)
{
std::string loc_bookname, loc_def, loc_exp;
std::string loc_bookname, loc_def, loc_exp;
if (!utf8_output_) {
loc_bookname = utf8_to_locale_ign_err(res.bookname);
loc_def = utf8_to_locale_ign_err(res.def);
loc_exp = utf8_to_locale_ign_err(res.exp);
}
if (json_) {
if (!first_result) {
fputs(",", out);
} else {
first_result = false;
}
fprintf(out, "{\"dict\": \"%s\",\"word\":\"%s\",\"definition\":\"%s\"}",
json_escape_string(res.bookname).c_str(),
json_escape_string(res.def).c_str(),
json_escape_string(res.exp).c_str());
if (!utf8_output_){
loc_bookname = utf8_to_locale_ign_err(res.bookname);
loc_def = utf8_to_locale_ign_err(res.def);
loc_exp = utf8_to_locale_ign_err(res.exp);
}
} else {
fprintf(out,
"-->%s%s%s\n"
"-->%s%s%s\n"
"%s\n\n",
colorize_output_ ? NAME_OF_DICT_VISFMT : "",
utf8_output_ ? res.bookname.c_str() : loc_bookname.c_str(),
colorize_output_ ? ESC_END : "",
colorize_output_ ? SEARCH_TERM_VISFMT : "",
utf8_output_ ? res.def.c_str() : loc_def.c_str(),
colorize_output_ ? ESC_END : "",
utf8_output_ ? res.exp.c_str() : loc_exp.c_str());
}
fprintf(out,
"-->%s%s%s\n"
"-->%s%s%s\n"
"%s\n\n",
colorize_output_ ? NAME_OF_DICT_VISFMT : "",
utf8_output_ ? res.bookname.c_str() : loc_bookname.c_str(),
colorize_output_ ? ESC_END : "",
colorize_output_ ? SEARCH_TERM_VISFMT : "",
utf8_output_ ? res.def.c_str() : loc_def.c_str(),
colorize_output_ ? ESC_END : "",
utf8_output_ ? res.exp.c_str() : loc_exp.c_str());
}
namespace
{
class sdcv_pager final
{
public:
explicit sdcv_pager(bool ignore_env = false)
{
output = stdout;
if (ignore_env) {
return;
}
const gchar *pager = g_getenv("SDCV_PAGER");
if (pager && (output = popen(pager, "w")) == nullptr) {
perror(_("popen failed"));
namespace {
class sdcv_pager {
public:
sdcv_pager(bool ignore_env = false) {
output = stdout;
if (ignore_env)
return;
const gchar *pager = g_getenv("SDCV_PAGER");
if (pager && (output = popen(pager, "w")) == nullptr) {
perror(_("popen failed"));
output = stdout;
}
}
}
sdcv_pager(const sdcv_pager &) = delete;
sdcv_pager &operator=(const sdcv_pager &) = delete;
~sdcv_pager()
{
if (output != stdout) {
pclose(output);
sdcv_pager(const sdcv_pager&) = delete;
sdcv_pager& operator=(const sdcv_pager&) = delete;
~sdcv_pager() {
if (output != stdout)
fclose(output);
}
}
FILE *get_stream() { return output; }
FILE *get_stream() { return output; }
private:
FILE *output;
};
}
private:
FILE *output;
};
} // namespace
search_result Library::process_phrase(const char *loc_str, IReadLine &io, bool force)
bool Library::process_phrase(const char *loc_str, IReadLine &io, bool force)
{
if (nullptr == loc_str)
return SEARCH_SUCCESS;
if (nullptr == loc_str)
return true;
std::string query;
std::string query;
analyze_query(loc_str, query);
if (!query.empty())
io.add_to_history(query.c_str());
analyze_query(loc_str, query);
if (!query.empty())
io.add_to_history(query.c_str());
gsize bytes_read;
gsize bytes_written;
gsize bytes_read;
gsize bytes_written;
glib::Error err;
search_result rval = SEARCH_SUCCESS;
glib::CharStr str;
if (!utf8_input_)
str.reset(g_locale_to_utf8(loc_str, -1, &bytes_read, &bytes_written, get_addr(err)));
else
str.reset(g_strdup(loc_str));
if (!utf8_input_)
str.reset(g_locale_to_utf8(loc_str, -1, &bytes_read, &bytes_written, get_addr(err)));
else
str.reset(g_strdup(loc_str));
if (nullptr == get_impl(str)) {
fprintf(stderr, _("Can not convert %s to utf8.\n"), loc_str);
fprintf(stderr, "%s\n", err->message);
return SEARCH_FAILURE;
}
if (nullptr == get_impl(str)) {
fprintf(stderr, _("Can not convert %s to utf8.\n"), loc_str);
fprintf(stderr, "%s\n", err->message);
return false;
}
if (str[0] == '\0')
return SEARCH_SUCCESS;
if (str[0] == '\0')
return true;
TSearchResultList res_list;
TSearchResultList res_list;
switch (analyze_query(get_impl(str), query)) {
case qtFUZZY:
LookupWithFuzzy(query, res_list);
break;
case qtREGEXP:
LookupWithRule(query, res_list);
break;
case qtSIMPLE:
SimpleLookup(get_impl(str), res_list);
if (res_list.empty() && fuzzy_)
LookupWithFuzzy(get_impl(str), res_list);
break;
case qtDATA:
LookupData(query, res_list);
break;
default:
/*nothing*/;
}
switch (analyze_query(get_impl(str), query)) {
case qtFUZZY:
LookupWithFuzzy(query, res_list);
break;
case qtREGEXP:
LookupWithRule(query, res_list);
break;
case qtSIMPLE:
SimpleLookup(get_impl(str), res_list);
if (res_list.empty())
LookupWithFuzzy(get_impl(str), res_list);
break;
case qtDATA:
LookupData(query, res_list);
break;
default:
/*nothing*/;
}
bool first_result = true;
if (json_) {
fputc('[', stdout);
}
if (!res_list.empty()) {
/* try to be more clever, if there are
if (!res_list.empty()) {
/* try to be more clever, if there are
one or zero results per dictionary show all
*/
bool show_all_results = true;
typedef std::map<std::string, int, std::less<std::string>> DictResMap;
if (!force) {
DictResMap res_per_dict;
for (const TSearchResult &search_res : res_list) {
auto r = res_per_dict.equal_range(search_res.bookname);
DictResMap tmp(r.first, r.second);
if (tmp.empty()) //there are no yet such bookname in map
res_per_dict.insert(DictResMap::value_type(search_res.bookname, 1));
else {
++((tmp.begin())->second);
if (tmp.begin()->second > 1) {
show_all_results = false;
break;
}
}
}
} //if (!force)
bool show_all_results = true;
typedef std::map< std::string, int, std::less<std::string> > DictResMap;
if (!force) {
DictResMap res_per_dict;
for (const TSearchResult& search_res : res_list) {
auto r = res_per_dict.equal_range(search_res.bookname);
DictResMap tmp(r.first, r.second);
if (tmp.empty()) //there are no yet such bookname in map
res_per_dict.insert(DictResMap::value_type(search_res.bookname, 1));
else {
++((tmp.begin())->second);
if (tmp.begin()->second > 1) {
show_all_results = false;
break;
}
}
}
}//if (!force)
if (!show_all_results && !force) {
if (!json_) {
printf(_("Found %zu items, similar to %s.\n"), res_list.size(),
utf8_output_ ? get_impl(str) : utf8_to_locale_ign_err(get_impl(str)).c_str());
}
for (size_t i = 0; i < res_list.size(); ++i) {
if (!show_all_results && !force) {
printf(_("Found %zu items, similar to %s.\n"), res_list.size(),
utf8_output_ ? get_impl(str) : utf8_to_locale_ign_err(get_impl(str)).c_str());
for (size_t i = 0; i < res_list.size(); ++i) {
const std::string loc_bookname = utf8_to_locale_ign_err(res_list[i].bookname);
const std::string loc_def = utf8_to_locale_ign_err(res_list[i].def);
printf("%zu)%s%s%s-->%s%s%s\n", i,
printf("%zu)%s%s%s-->%s%s%s\n", i,
colorize_output_ ? NAME_OF_DICT_VISFMT : "",
utf8_output_ ? res_list[i].bookname.c_str() : loc_bookname.c_str(),
utf8_output_ ? res_list[i].bookname.c_str() : loc_bookname.c_str(),
colorize_output_ ? ESC_END : "",
colorize_output_ ? SEARCH_TERM_VISFMT : "",
utf8_output_ ? res_list[i].def.c_str() : loc_def.c_str(),
utf8_output_ ? res_list[i].def.c_str() : loc_def.c_str(),
colorize_output_ ? ESC_END : "");
}
int choise;
std::unique_ptr<IReadLine> choice_readline(create_readline_object());
for (;;) {
}
int choise;
std::unique_ptr<IReadLine> choice_readline(create_readline_object());
for (;;) {
std::string str_choise;
choice_readline->read(_("Your choice[-1 to abort]: "), str_choise);
sscanf(str_choise.c_str(), "%d", &choise);
if (choise >= 0 && choise < int(res_list.size())) {
sdcv_pager pager;
choice_readline->read(_("Your choice[-1 to abort]: "), str_choise);
sscanf(str_choise.c_str(), "%d", &choise);
if (choise >= 0 && choise < int(res_list.size())) {
sdcv_pager pager;
io.add_to_history(res_list[choise].def.c_str());
print_search_result(pager.get_stream(), res_list[choise], first_result);
break;
} else if (choise == -1) {
break;
} else
printf(_("Invalid choice.\nIt must be from 0 to %zu or -1.\n"),
res_list.size() - 1);
}
} else {
sdcv_pager pager(force || json_);
if (!json_) {
fprintf(pager.get_stream(), _("Found %zu items, similar to %s.\n"),
res_list.size(), utf8_output_ ? get_impl(str) : utf8_to_locale_ign_err(get_impl(str)).c_str());
}
for (const TSearchResult &search_res : res_list) {
print_search_result(pager.get_stream(), search_res, first_result);
}
}
print_search_result(pager.get_stream(), res_list[choise]);
break;
} else if (choise == -1){
break;
} else
printf(_("Invalid choice.\nIt must be from 0 to %zu or -1.\n"),
res_list.size()-1);
}
} else {
sdcv_pager pager(force);
fprintf(pager.get_stream(), _("Found %zu items, similar to %s.\n"),
res_list.size(), utf8_output_ ? get_impl(str) : utf8_to_locale_ign_err(get_impl(str)).c_str());
for (const TSearchResult& search_res : res_list)
print_search_result(pager.get_stream(), search_res);
}
} else {
std::string loc_str;
if (!utf8_output_)
loc_str = utf8_to_locale_ign_err(get_impl(str));
if (!json_)
printf(_("Nothing similar to %s, sorry :(\n"), utf8_output_ ? get_impl(str) : loc_str.c_str());
rval = SEARCH_NO_RESULT;
}
} else {
std::string loc_str;
if (!utf8_output_)
loc_str = utf8_to_locale_ign_err(get_impl(str));
if (json_) {
fputs("]\n", stdout);
}
return rval;
printf(_("Nothing similar to %s, sorry :(\n"), utf8_output_ ? get_impl(str) : loc_str.c_str());
}
return true;
}

56
src/libwrapper.hpp
View File

@@ -3,59 +3,41 @@
#include <string>
#include <vector>
#include "readline.hpp"
#include "stardict_lib.hpp"
#include "readline.hpp"
//this structure is wrapper and it need for unification
//results of search whith return Dicts class
struct TSearchResult {
std::string bookname;
std::string def;
std::string exp;
std::string bookname;
std::string def;
std::string exp;
TSearchResult(const std::string &bookname_, const std::string &def_, const std::string &exp_)
: bookname(bookname_)
, def(def_)
, exp(exp_)
{
}
TSearchResult(const std::string& bookname_, const std::string& def_, const std::string& exp_)
: bookname(bookname_), def(def_), exp(exp_)
{
}
};
typedef std::vector<TSearchResult> TSearchResultList;
//possible return values for Library.process_phase()
enum search_result {
SEARCH_SUCCESS = 0,
SEARCH_FAILURE,
SEARCH_NO_RESULT
};
//this class is wrapper around Dicts class for easy use
//of it
class Library : public Libs
{
class Library : public Libs {
public:
Library(bool uinput, bool uoutput, bool colorize_output, bool use_json, bool no_fuzzy)
: utf8_input_(uinput)
, utf8_output_(uoutput)
, colorize_output_(colorize_output)
, json_(use_json)
{
setVerbose(!use_json);
setFuzzy(!no_fuzzy);
}
search_result process_phrase(const char *loc_str, IReadLine &io, bool force = false);
Library(bool uinput, bool uoutput, bool colorize_output):
utf8_input_(uinput), utf8_output_(uoutput), colorize_output_(colorize_output) {}
bool process_phrase(const char *loc_str, IReadLine &io, bool force = false);
private:
bool utf8_input_;
bool utf8_input_;
bool utf8_output_;
bool colorize_output_;
bool json_;
void SimpleLookup(const std::string &str, TSearchResultList &res_list);
void LookupWithFuzzy(const std::string &str, TSearchResultList &res_list);
void LookupWithRule(const std::string &str, TSearchResultList &res_lsit);
void LookupData(const std::string &str, TSearchResultList &res_list);
void print_search_result(FILE *out, const TSearchResult &res, bool &first_result);
void SimpleLookup(const std::string &str, TSearchResultList& res_list);
void LookupWithFuzzy(const std::string &str, TSearchResultList& res_list);
void LookupWithRule(const std::string &str, TSearchResultList& res_lsit);
void LookupData(const std::string &str, TSearchResultList& res_list);
void print_search_result(FILE *out, const TSearchResult & res);
};

67
src/main.rs Normal file
View File

@@ -0,0 +1,67 @@
extern crate getopts;
extern crate gettext;
extern crate ini;
extern crate byteorder;
extern crate libc;
extern crate flate2;
mod core;
mod index;
mod data;
mod mem_mapped_file;
use core::Dictionary;
use std::env;
use std::result::Result;
use getopts::Options;
use gettext::Catalog;
use std::fs::File;
use std::path::Path;
struct Library {
dicts : Vec<Dictionary>
}
impl Library {
fn new(dict_dirs: &[&Path], dict_order_names: &[String], dict_disable_names: &[String]) -> Result<Library, String> {
let dicts = vec![Dictionary::new(Path::new("/home/evgeniy/.stardict/dic/stardict-Mueller7accentGPL-2.4.2/Mueller7accentGPL.ifo")).unwrap()];
Ok(Library{dicts: dicts})
}
pub fn simple_lookup(&mut self, phrase: &str) /*-> Option<String>*/ {
for dict in self.dicts.iter_mut() {
if let Some(translation) = dict.find(phrase) {
println!("{}", translation);
}
}
}
}
fn print_usage(program: &str, opts: Options) {
let brief = format!("Usage: {} [options] [list of words]", program);
print!("{}", opts.usage(&brief));
}
fn main() {
let translation_f = File::open("/usr/share/locale/ru/LC_MESSAGES/sdcv.mo").expect("could not open the catalog");
let catalog = Catalog::parse(translation_f).expect("could not parse the catalog");
let args: Vec<String> = env::args().collect();
let program = args[0].clone();
let mut opts = Options::new();
opts.optflag("v", "version", catalog.gettext("display version information and exit"));
opts.optflag("h", "help", catalog.gettext("Show help options"));
let matches = match opts.parse(&args[1..]) {
Ok(m) => { m }
Err(f) => { panic!(f.to_string()) }
};
if matches.opt_present("h") {
print_usage(&program, opts);
return;
}
let dict_dirs = vec![Path::new("/tmp")];
let dict_order_names: Vec<String> = vec![];
let dict_disable_names: Vec<String> = vec![];
let mut library = Library::new(&dict_dirs, &dict_order_names, &dict_disable_names).unwrap();
library.simple_lookup("man");
}

95
src/mapfile.hpp
View File

@@ -1,30 +1,27 @@
#pragma once
#ifdef HAVE_CONFIG_H
#include "config.h"
# include "config.h"
#endif
#ifdef HAVE_MMAP
#include <fcntl.h>
#include <sys/mman.h>
#include <sys/stat.h>
#include <sys/types.h>
# include <sys/types.h>
# include <fcntl.h>
# include <sys/mman.h>
#endif
#ifdef _WIN32
#include <windows.h>
# include <windows.h>
#endif
#include <glib.h>
class MapFile
{
class MapFile {
public:
MapFile() {}
~MapFile();
MapFile(const MapFile &) = delete;
MapFile &operator=(const MapFile &) = delete;
MapFile(const MapFile&) = delete;
MapFile& operator=(const MapFile&) = delete;
bool open(const char *file_name, unsigned long file_size);
gchar *begin() { return data; }
private:
char *data = nullptr;
unsigned long size = 0ul;
@@ -38,55 +35,51 @@ private:
inline bool MapFile::open(const char *file_name, unsigned long file_size)
{
size = file_size;
size=file_size;
#ifdef HAVE_MMAP
if ((mmap_fd = ::open(file_name, O_RDONLY)) < 0) {
// g_print("Open file %s failed!\n",fullfilename);
return false;
}
struct stat st;
if (fstat(mmap_fd, &st) == -1 || st.st_size < 0 || (st.st_size == 0 && S_ISREG(st.st_mode))
|| sizeof(st.st_size) > sizeof(file_size) || static_cast<unsigned long>(st.st_size) != file_size) {
close(mmap_fd);
return false;
}
data = (gchar *)mmap(nullptr, file_size, PROT_READ, MAP_SHARED, mmap_fd, 0);
if ((void *)data == (void *)(-1)) {
// g_print("mmap file %s failed!\n",idxfilename);
data = nullptr;
return false;
}
#elif defined(_WIN32)
hFile = CreateFile(file_name, GENERIC_READ, 0, nullptr, OPEN_ALWAYS, FILE_ATTRIBUTE_NORMAL, 0);
hFileMap = CreateFileMapping(hFile, nullptr, PAGE_READONLY, 0, file_size, nullptr);
data = (gchar *)MapViewOfFile(hFileMap, FILE_MAP_READ, 0, 0, file_size);
if ((mmap_fd = ::open(file_name, O_RDONLY)) < 0) {
//g_print("Open file %s failed!\n",fullfilename);
return false;
}
data = (gchar *)mmap( nullptr, file_size, PROT_READ, MAP_SHARED, mmap_fd, 0);
if ((void *)data == (void *)(-1)) {
//g_print("mmap file %s failed!\n",idxfilename);
data=nullptr;
return false;
}
#elif defined( _WIN32)
hFile = CreateFile(file_name, GENERIC_READ, 0, nullptr, OPEN_ALWAYS,
FILE_ATTRIBUTE_NORMAL, 0);
hFileMap = CreateFileMapping(hFile, nullptr, PAGE_READONLY, 0,
file_size, nullptr);
data = (gchar *)MapViewOfFile(hFileMap, FILE_MAP_READ, 0, 0, file_size);
#else
gsize read_len;
if (!g_file_get_contents(file_name, &data, &read_len, nullptr))
return false;
gsize read_len;
if (!g_file_get_contents(file_name, &data, &read_len, nullptr))
return false;
if (read_len != file_size)
return false;
if (read_len != file_size)
return false;
#endif
return true;
return true;
}
inline MapFile::~MapFile()
{
if (!data)
return;
if (!data)
return;
#ifdef HAVE_MMAP
munmap(data, size);
close(mmap_fd);
munmap(data, size);
close(mmap_fd);
#else
#ifdef _WIN32
UnmapViewOfFile(data);
CloseHandle(hFileMap);
CloseHandle(hFile);
#else
g_free(data);
#endif
#endif
# ifdef _WIN32
UnmapViewOfFile(data);
CloseHandle(hFileMap);
CloseHandle(hFile);
# else
g_free(data);
# endif
#endif
}

179
src/mem_mapped_file.rs Normal file
View File

@@ -0,0 +1,179 @@
use std::path::Path;
use std::fs::File;
use std::os::unix::io::AsRawFd;
use std::ptr;
use std::slice;
use libc::{c_void, c_int};
use libc;
pub struct MemMappedFile {
mem_addr: *const u8,
length: usize,
}
#[cfg(unix)]
impl MemMappedFile {
pub fn new(file_name: &Path) -> Result<MemMappedFile, String> {
let file = try!(File::open(file_name).map_err(|err| err.to_string()));
let metadata = try!(file.metadata().map_err(|err| err.to_string()));
if !metadata.is_file() {
return Err(format!("{} is not file", file_name.to_str().unwrap()));
}
let file_len = metadata.len();
let fd = file.as_raw_fd();
let addr: *const u8 = ptr::null();
let res = unsafe {
libc::mmap(addr as *mut c_void, file_len as libc::size_t, libc::PROT_READ, libc::MAP_SHARED,
fd, 0)
};
if res == libc::MAP_FAILED {
Err(format!("mmap for {} failed", file_name.to_str().unwrap()))
} else {
Ok(MemMappedFile{mem_addr: res as *mut u8, length: file_len as usize})
}
}
pub fn len(&self) -> usize { self.length }
pub fn get_chunk<'a>(&self, offset: usize, size: usize) -> Result<&'a[u8], String> {
let end = offset + size;
if end > self.length {
return Err(format!("offset out of range from 0 to {}", self.length));
}
Ok(unsafe {slice::from_raw_parts(self.mem_addr.offset(offset as isize), size) })
}
}
#[cfg(unix)]
impl Drop for MemMappedFile {
fn drop(&mut self) {
let res: c_int = unsafe {
// `munmap` only panics due to logic errors
libc::munmap(self.mem_addr as *mut c_void, self.length as libc::size_t)
};
if res == -1 {
panic!("munmap return error");
}
}
}
#[cfg(test)]
mod test {
use super::*;
use std::path::Path;
use std::mem;
use std::slice;
static CRCTAB: [u32; 256] = [
0x00000000,
0x04c11db7, 0x09823b6e, 0x0d4326d9, 0x130476dc, 0x17c56b6b,
0x1a864db2, 0x1e475005, 0x2608edb8, 0x22c9f00f, 0x2f8ad6d6,
0x2b4bcb61, 0x350c9b64, 0x31cd86d3, 0x3c8ea00a, 0x384fbdbd,
0x4c11db70, 0x48d0c6c7, 0x4593e01e, 0x4152fda9, 0x5f15adac,
0x5bd4b01b, 0x569796c2, 0x52568b75, 0x6a1936c8, 0x6ed82b7f,
0x639b0da6, 0x675a1011, 0x791d4014, 0x7ddc5da3, 0x709f7b7a,
0x745e66cd, 0x9823b6e0, 0x9ce2ab57, 0x91a18d8e, 0x95609039,
0x8b27c03c, 0x8fe6dd8b, 0x82a5fb52, 0x8664e6e5, 0xbe2b5b58,
0xbaea46ef, 0xb7a96036, 0xb3687d81, 0xad2f2d84, 0xa9ee3033,
0xa4ad16ea, 0xa06c0b5d, 0xd4326d90, 0xd0f37027, 0xddb056fe,
0xd9714b49, 0xc7361b4c, 0xc3f706fb, 0xceb42022, 0xca753d95,
0xf23a8028, 0xf6fb9d9f, 0xfbb8bb46, 0xff79a6f1, 0xe13ef6f4,
0xe5ffeb43, 0xe8bccd9a, 0xec7dd02d, 0x34867077, 0x30476dc0,
0x3d044b19, 0x39c556ae, 0x278206ab, 0x23431b1c, 0x2e003dc5,
0x2ac12072, 0x128e9dcf, 0x164f8078, 0x1b0ca6a1, 0x1fcdbb16,
0x018aeb13, 0x054bf6a4, 0x0808d07d, 0x0cc9cdca, 0x7897ab07,
0x7c56b6b0, 0x71159069, 0x75d48dde, 0x6b93dddb, 0x6f52c06c,
0x6211e6b5, 0x66d0fb02, 0x5e9f46bf, 0x5a5e5b08, 0x571d7dd1,
0x53dc6066, 0x4d9b3063, 0x495a2dd4, 0x44190b0d, 0x40d816ba,
0xaca5c697, 0xa864db20, 0xa527fdf9, 0xa1e6e04e, 0xbfa1b04b,
0xbb60adfc, 0xb6238b25, 0xb2e29692, 0x8aad2b2f, 0x8e6c3698,
0x832f1041, 0x87ee0df6, 0x99a95df3, 0x9d684044, 0x902b669d,
0x94ea7b2a, 0xe0b41de7, 0xe4750050, 0xe9362689, 0xedf73b3e,
0xf3b06b3b, 0xf771768c, 0xfa325055, 0xfef34de2, 0xc6bcf05f,
0xc27dede8, 0xcf3ecb31, 0xcbffd686, 0xd5b88683, 0xd1799b34,
0xdc3abded, 0xd8fba05a, 0x690ce0ee, 0x6dcdfd59, 0x608edb80,
0x644fc637, 0x7a089632, 0x7ec98b85, 0x738aad5c, 0x774bb0eb,
0x4f040d56, 0x4bc510e1, 0x46863638, 0x42472b8f, 0x5c007b8a,
0x58c1663d, 0x558240e4, 0x51435d53, 0x251d3b9e, 0x21dc2629,
0x2c9f00f0, 0x285e1d47, 0x36194d42, 0x32d850f5, 0x3f9b762c,
0x3b5a6b9b, 0x0315d626, 0x07d4cb91, 0x0a97ed48, 0x0e56f0ff,
0x1011a0fa, 0x14d0bd4d, 0x19939b94, 0x1d528623, 0xf12f560e,
0xf5ee4bb9, 0xf8ad6d60, 0xfc6c70d7, 0xe22b20d2, 0xe6ea3d65,
0xeba91bbc, 0xef68060b, 0xd727bbb6, 0xd3e6a601, 0xdea580d8,
0xda649d6f, 0xc423cd6a, 0xc0e2d0dd, 0xcda1f604, 0xc960ebb3,
0xbd3e8d7e, 0xb9ff90c9, 0xb4bcb610, 0xb07daba7, 0xae3afba2,
0xaafbe615, 0xa7b8c0cc, 0xa379dd7b, 0x9b3660c6, 0x9ff77d71,
0x92b45ba8, 0x9675461f, 0x8832161a, 0x8cf30bad, 0x81b02d74,
0x857130c3, 0x5d8a9099, 0x594b8d2e, 0x5408abf7, 0x50c9b640,
0x4e8ee645, 0x4a4ffbf2, 0x470cdd2b, 0x43cdc09c, 0x7b827d21,
0x7f436096, 0x7200464f, 0x76c15bf8, 0x68860bfd, 0x6c47164a,
0x61043093, 0x65c52d24, 0x119b4be9, 0x155a565e, 0x18197087,
0x1cd86d30, 0x029f3d35, 0x065e2082, 0x0b1d065b, 0x0fdc1bec,
0x3793a651, 0x3352bbe6, 0x3e119d3f, 0x3ad08088, 0x2497d08d,
0x2056cd3a, 0x2d15ebe3, 0x29d4f654, 0xc5a92679, 0xc1683bce,
0xcc2b1d17, 0xc8ea00a0, 0xd6ad50a5, 0xd26c4d12, 0xdf2f6bcb,
0xdbee767c, 0xe3a1cbc1, 0xe760d676, 0xea23f0af, 0xeee2ed18,
0xf0a5bd1d, 0xf464a0aa, 0xf9278673, 0xfde69bc4, 0x89b8fd09,
0x8d79e0be, 0x803ac667, 0x84fbdbd0, 0x9abc8bd5, 0x9e7d9662,
0x933eb0bb, 0x97ffad0c, 0xafb010b1, 0xab710d06, 0xa6322bdf,
0xa2f33668, 0xbcb4666d, 0xb8757bda, 0xb5365d03, 0xb1f740b4
];
fn crc32(buf: &[u32]) -> u32 {
let mut crc = 0_u32;
for item in buf {
let mut byte: u32 = item & 0xFF_u32;
crc = (crc << 8) ^ CRCTAB[(((crc >> 24) ^ byte) & 0xFF) as usize];
byte = (item >> 8) & 0xFF_u32;
crc = (crc << 8) ^ CRCTAB[(((crc >> 24) ^ byte) & 0xFF) as usize];
byte = (item >> 16) & 0xFF_u32;
crc = (crc << 8) ^ CRCTAB[(((crc >> 24) ^ byte) & 0xFF) as usize];
byte = (item >> 24) & 0xFF_u32;
crc = (crc << 8) ^ CRCTAB[(((crc >> 24) ^ byte) & 0xFF) as usize];
}
!crc & 0xFFFFFFFF_u32
}
#[test]
fn mem_mapped_file_basic_test() {
let mfile = MemMappedFile::new(Path::new("tests/words_dic/stardict-words-2.4.2/words.idx")).unwrap();
let mem_chunk = mfile.get_chunk(0, 16).unwrap();
assert_eq!(mem_chunk.len(), 16);
let exp : Vec<u8> = vec![0x21, 0, 0, 0, 0, 0, 0, 0, 0, 0xa, 0x21, 0x20, 0x23, 0x24, 0x25, 0x5e];
assert_eq!(mem_chunk, exp.as_slice());
const CHUNK_SIZE: usize = 256;
let n_chunks = (mfile.len() + CHUNK_SIZE -1) / CHUNK_SIZE;
let mut data: Vec<u32> = Vec::with_capacity(mfile.len() / 4);
for i in 0..(n_chunks - 1) {
let mem_chunk = mfile.get_chunk(i * CHUNK_SIZE, CHUNK_SIZE).unwrap();
let data_bytes = &mem_chunk[0] as *const u8;
let data_words: *const u32 = unsafe { mem::transmute(data_bytes) };
let chunk_u32_view = unsafe { slice::from_raw_parts(data_words, CHUNK_SIZE / 4) };
data.extend_from_slice(chunk_u32_view);
}
let res_crc = crc32(data.as_slice());
assert_eq!(res_crc, 0x2a04c834_u32);
let rest = mfile.len() - (n_chunks - 1) * CHUNK_SIZE;
if rest > 0 {
let mem_chunk = mfile.get_chunk((n_chunks - 1) * CHUNK_SIZE, rest).unwrap();
let add_size = (rest + 3) / 4;
for i in 0..add_size {
let mut word = 0_u32;
for j in 0..4 {
if i * 4 + j < mem_chunk.len() {
word |= (mem_chunk[i * 4 + j] as u32) << (j * 8);
}
}
data.push(word);
}
}
let res_crc = crc32(data.as_slice());
assert_eq!(res_crc, 0x6ae491df);
}
}

142
src/readline.cpp
View File

@@ -1,4 +1,4 @@
/*
/*
* This file part of sdcv - console version of Stardict program
* http://sdcv.sourceforge.net
* Copyright (C) 2005 Evgeniy <dushistov@mail.ru>
@@ -15,18 +15,18 @@
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
# include "config.h"
#endif
#include <cstdio>
#include <cstdlib>
#ifdef WITH_READLINE
#include <readline/history.h>
#include <readline/readline.h>
# include <readline/readline.h>
# include <readline/history.h>
#endif
#include <glib.h>
@@ -34,96 +34,72 @@
#include "readline.hpp"
bool stdio_getline(FILE *in, std::string &str)
{
assert(in != nullptr);
str.clear();
int ch;
while ((ch = fgetc(in)) != EOF && ch != '\n')
str += ch;
return EOF != ch;
}
#ifndef WITH_READLINE
namespace
{
class dummy_readline : public IReadLine
{
public:
bool read(const std::string &banner, std::string &line) override
namespace {
static bool stdio_getline(FILE *in, std::string & str)
{
printf("%s", banner.c_str());
return stdio_getline(stdin, line);
str.clear();
int ch;
while ((ch=fgetc(in)) != EOF && ch != '\n')
str += ch;
return EOF != ch;
}
};
} // namespace
class dummy_readline : public IReadLine {
public:
bool read(const string& banner, string& line) override {
printf("%s", banner.c_str());
return stdio_getline(stdin, line);
}
};
}
#else
namespace
{
std::string get_hist_file_path()
{
const gchar *hist_file_str = g_getenv("SDCV_HISTFILE");
namespace {
class real_readline : public IReadLine {
if (hist_file_str != nullptr)
return std::string(hist_file_str);
const std::string hist_file_path = std::string(g_get_home_dir()) + G_DIR_SEPARATOR + ".sdcv_history";
if (g_file_test(hist_file_path.c_str(), G_FILE_TEST_IS_REGULAR))
return hist_file_path;
return std::string(g_get_user_data_dir()) + G_DIR_SEPARATOR + "sdcv_history";
}
class real_readline : public IReadLine
{
public:
real_readline()
{
rl_readline_name = "sdcv";
using_history();
const std::string histname = get_hist_file_path();
read_history(histname.c_str());
}
~real_readline()
{
const std::string histname = get_hist_file_path();
write_history(histname.c_str());
const gchar *hist_size_str = g_getenv("SDCV_HISTSIZE");
int hist_size;
if (!hist_size_str || sscanf(hist_size_str, "%d", &hist_size) < 1)
hist_size = 2000;
history_truncate_file(histname.c_str(), hist_size);
}
bool read(const std::string &banner, std::string &line) override
{
char *phrase = nullptr;
phrase = readline(banner.c_str());
if (phrase) {
line = phrase;
free(phrase);
return true;
public:
real_readline() {
rl_readline_name = "sdcv";
using_history();
const std::string histname = std::string(g_get_home_dir()) + G_DIR_SEPARATOR + ".sdcv_history";
read_history(histname.c_str());
}
return false;
}
void add_to_history(const std::string &phrase) override
{
add_history(phrase.c_str());
}
};
} // namespace
#endif //WITH_READLINE
~real_readline() {
const std::string histname = std::string(g_get_home_dir()) + G_DIR_SEPARATOR + ".sdcv_history";
write_history(histname.c_str());
const gchar *hist_size_str=g_getenv("SDCV_HISTSIZE");
int hist_size;
if (!hist_size_str || sscanf(hist_size_str, "%d", &hist_size)<1)
hist_size = 2000;
history_truncate_file(histname.c_str(), hist_size);
}
bool read(const std::string &banner, std::string& line) override {
char *phrase = nullptr;
phrase = readline(banner.c_str());
if (phrase) {
line = phrase;
free(phrase);
return true;
}
return false;
}
void add_to_history(const std::string& phrase) override {
add_history(phrase.c_str());
}
};
}
#endif//WITH_READLINE
IReadLine *create_readline_object()
{
#ifdef WITH_READLINE
return new real_readline;
return new real_readline;
#else
return new dummy_readline;
return new dummy_readline;
#endif
}

11
src/readline.hpp
View File

@@ -2,14 +2,13 @@
#include <string>
class IReadLine
{
class IReadLine {
public:
virtual ~IReadLine() {}
virtual bool read(const std::string &banner, std::string &line) = 0;
virtual void add_to_history(const std::string &) {}
virtual ~IReadLine() {}
virtual bool read(const std::string &banner, std::string& line) = 0;
virtual void add_to_history(const std::string&) {}
};
extern std::string sdcv_readline;
extern IReadLine *create_readline_object();
extern bool stdio_getline(FILE *in, std::string &str);

183
src/sdcv.cpp
View File

@@ -1,4 +1,4 @@
/*
/*
* This file part of sdcv - console version of Stardict program
* http://sdcv.sourceforge.net
* Copyright (C) 2003-2006 Evgeniy <dushistov@mail.ru>
@@ -15,20 +15,18 @@
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include <algorithm>
#include <cerrno>
#include <clocale>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <map>
#include <memory>
#include <string>
#include <vector>
@@ -53,22 +51,19 @@ static void free_str_array(gchar **arr)
g_free(*p);
g_free(arr);
}
} // namespace
}
namespace glib
{
using StrArr = ResourceWrapper<gchar *, gchar *, free_str_array>;
typedef ResourceWrapper<gchar *, gchar *, free_str_array> StrArr;
}
static void list_dicts(const std::list<std::string> &dicts_dir_list, bool use_json);
int main(int argc, char *argv[])
try {
int main(int argc, char *argv[]) try {
setlocale(LC_ALL, "");
#if ENABLE_NLS
bindtextdomain("sdcv",
//"./locale"//< for testing
GETTEXT_TRANSLATIONS_PATH //< should be
);
);
textdomain("sdcv");
#endif
@@ -76,14 +71,10 @@ try {
gboolean show_list_dicts = FALSE;
glib::StrArr use_dict_list;
gboolean non_interactive = FALSE;
gboolean json_output = FALSE;
gboolean no_fuzzy = FALSE;
gboolean utf8_output = FALSE;
gboolean utf8_input = FALSE;
glib::CharStr opt_data_dir;
gboolean only_data_dir = FALSE;
gboolean colorize = FALSE;
glib::StrArr word_list;
const GOptionEntry entries[] = {
{ "version", 'v', 0, G_OPTION_ARG_NONE, &show_version,
@@ -95,12 +86,6 @@ try {
_("bookname") },
{ "non-interactive", 'n', 0, G_OPTION_ARG_NONE, &non_interactive,
_("for use in scripts"), nullptr },
{ "json-output", 'j', 0, G_OPTION_ARG_NONE, &json_output,
_("print the result formatted as JSON"), nullptr },
{ "json", 'j', 0, G_OPTION_ARG_NONE, &json_output,
_("print the result formatted as JSON"), nullptr },
{ "exact-search", 'e', 0, G_OPTION_ARG_NONE, &no_fuzzy,
_("do not fuzzy-search for similar words, only return exact matches"), nullptr },
{ "utf8-output", '0', 0, G_OPTION_ARG_NONE, &utf8_output,
_("output must be in utf8"), nullptr },
{ "utf8-input", '1', 0, G_OPTION_ARG_NONE, &utf8_input,
@@ -108,17 +93,13 @@ try {
{ "data-dir", '2', 0, G_OPTION_ARG_STRING, get_addr(opt_data_dir),
_("use this directory as path to stardict data directory"),
_("path/to/dir") },
{ "only-data-dir", 'x', 0, G_OPTION_ARG_NONE, &only_data_dir,
_("only use the dictionaries in data-dir, do not search in user and system directories"), nullptr },
{ "color", 'c', 0, G_OPTION_ARG_NONE, &colorize,
_("colorize the output"), nullptr },
{ G_OPTION_REMAINING, 0, 0, G_OPTION_ARG_FILENAME_ARRAY, get_addr(word_list),
_("search terms"), _(" words") },
{},
{ nullptr },
};
glib::Error error;
GOptionContext *context = g_option_context_new(nullptr);
GOptionContext *context = g_option_context_new(_(" words"));
g_option_context_set_help_enabled(context, TRUE);
g_option_context_add_main_entries(context, entries, nullptr);
const gboolean parse_res = g_option_context_parse(context, &argc, &argv, get_addr(error));
@@ -137,100 +118,75 @@ try {
const gchar *stardict_data_dir = g_getenv("STARDICT_DATA_DIR");
std::string data_dir;
if (!opt_data_dir) {
if (!only_data_dir) {
if (stardict_data_dir)
data_dir = stardict_data_dir;
else
data_dir = "/usr/share/stardict/dic";
}
if (stardict_data_dir)
data_dir = stardict_data_dir;
else
data_dir = "/usr/share/stardict/dic";
} else {
data_dir = get_impl(opt_data_dir);
}
std::string conf_dir = std::string(g_get_home_dir()) + G_DIR_SEPARATOR + ".stardict";
if (!g_file_test(conf_dir.c_str(), G_FILE_TEST_IS_DIR))
conf_dir = std::string(g_get_user_data_dir()) + G_DIR_SEPARATOR + "stardict";
const char *homedir = g_getenv("HOME");
if (!homedir)
homedir = g_get_home_dir();
const std::list<std::string> dicts_dir_list = {
std::string(homedir) + G_DIR_SEPARATOR + ".stardict" + G_DIR_SEPARATOR + "dic",
data_dir
};
std::list<std::string> dicts_dir_list;
if (!only_data_dir)
dicts_dir_list.push_back(conf_dir + G_DIR_SEPARATOR + "dic");
dicts_dir_list.push_back(data_dir);
if (show_list_dicts) {
list_dicts(dicts_dir_list, json_output);
printf(_("Dictionary's name Word count\n"));
std::list<std::string> order_list, disable_list;
for_each_file(dicts_dir_list, ".ifo", order_list,
disable_list, [](const std::string &filename, bool) -> void {
DictInfo dict_info;
if (dict_info.load_from_ifo_file(filename, false)) {
const std::string bookname = utf8_to_locale_ign_err(dict_info.bookname);
printf("%s %d\n", bookname.c_str(), dict_info.wordcount);
}
});
return EXIT_SUCCESS;
}
std::list<std::string> disable_list;
std::map<std::string, std::string> bookname_to_ifo;
for_each_file(dicts_dir_list, ".ifo", std::list<std::string>(), std::list<std::string>(),
[&bookname_to_ifo](const std::string &fname, bool) {
DictInfo dict_info;
const bool load_ok = dict_info.load_from_ifo_file(fname, false);
if (!load_ok)
return;
bookname_to_ifo[dict_info.bookname] = dict_info.ifo_file_name;
});
if (use_dict_list) {
std::list<std::string> empty_list;
std::list<std::string> order_list;
if (use_dict_list != nullptr) {
for (auto &&x : bookname_to_ifo) {
gchar **p = get_impl(use_dict_list);
for (; *p != nullptr; ++p)
if (x.first.compare(*p) == 0) {
break;
}
if (*p == nullptr) {
disable_list.push_back(x.second);
}
}
for_each_file(dicts_dir_list, ".ifo", empty_list, empty_list,
[&disable_list, &use_dict_list](const std::string &filename, bool) -> void {
DictInfo dict_info;
const bool load_ok = dict_info.load_from_ifo_file(filename, false);
if (!load_ok)
return;
// add bookname to list
gchar **p = get_impl(use_dict_list);
while (*p) {
order_list.push_back(bookname_to_ifo.at(*p));
++p;
}
} else {
std::string ordering_cfg_file = std::string(g_get_user_config_dir()) + G_DIR_SEPARATOR_S "sdcv_ordering";
FILE *ordering_file = fopen(ordering_cfg_file.c_str(), "r");
if (ordering_file == nullptr) {
ordering_cfg_file = std::string(g_get_home_dir()) + G_DIR_SEPARATOR_S ".sdcv_ordering";
ordering_file = fopen(ordering_cfg_file.c_str(), "r");
}
if (ordering_file != nullptr) {
std::string line;
while (stdio_getline(ordering_file, line)) {
order_list.push_back(bookname_to_ifo.at(line));
}
fclose(ordering_file);
}
for (gchar **p = get_impl(use_dict_list); *p != nullptr; ++p)
if (strcmp(*p, dict_info.bookname.c_str()) == 0)
return;
disable_list.push_back(dict_info.ifo_file_name);
});
}
if (g_mkdir(conf_dir.c_str(), S_IRWXU) == -1 && errno != EEXIST) {
const std::string conf_dir = std::string(g_get_home_dir()) + G_DIR_SEPARATOR + ".stardict";
if (g_mkdir(conf_dir.c_str(), S_IRWXU) == -1 && errno != EEXIST)
fprintf(stderr, _("g_mkdir failed: %s\n"), strerror(errno));
}
Library lib(utf8_input, utf8_output, colorize, json_output, no_fuzzy);
lib.load(dicts_dir_list, order_list, disable_list);
Library lib(utf8_input, utf8_output, colorize);
std::list<std::string> empty_list;
lib.load(dicts_dir_list, empty_list, disable_list);
std::unique_ptr<IReadLine> io(create_readline_object());
if (word_list != nullptr) {
search_result rval = SEARCH_SUCCESS;
gchar **p = get_impl(word_list);
while (*p) {
search_result this_rval = lib.process_phrase(*p++, *io, non_interactive);
// If we encounter any error, save it but continue through the word
// list to check all requested words.
if (rval == SEARCH_SUCCESS)
rval = this_rval;
}
if (rval != SEARCH_SUCCESS)
return rval;
if (optind < argc) {
for (int i = optind; i < argc; ++i)
if (!lib.process_phrase(argv[i], *io, non_interactive))
return EXIT_FAILURE;
} else if (!non_interactive) {
std::string phrase;
while (io->read(_("Enter word or phrase: "), phrase)) {
if (lib.process_phrase(phrase.c_str(), *io) == SEARCH_FAILURE)
if (!lib.process_phrase(phrase.c_str(), *io))
return EXIT_FAILURE;
phrase.clear();
}
@@ -244,32 +200,3 @@ try {
fprintf(stderr, "Internal error: %s\n", ex.what());
exit(EXIT_FAILURE);
}
static void list_dicts(const std::list<std::string> &dicts_dir_list, bool use_json)
{
bool first_entry = true;
if (!use_json)
printf(_("Dictionary's name Word count\n"));
else
fputc('[', stdout);
std::list<std::string> order_list, disable_list;
for_each_file(dicts_dir_list, ".ifo", order_list,
disable_list, [use_json, &first_entry](const std::string &filename, bool) -> void {
DictInfo dict_info;
if (dict_info.load_from_ifo_file(filename, false)) {
const std::string bookname = utf8_to_locale_ign_err(dict_info.bookname);
if (use_json) {
if (first_entry) {
first_entry = false;
} else {
fputc(',', stdout); // comma between entries
}
printf("{\"name\": \"%s\", \"wordcount\": \"%d\"}", json_escape_string(bookname).c_str(), dict_info.wordcount);
} else {
printf("%s %d\n", bookname.c_str(), dict_info.wordcount);
}
}
});
if (use_json)
fputs("]\n", stdout);
}

2855
src/stardict_lib.cpp
View File

File diff suppressed because it is too large Load Diff

257
src/stardict_lib.hpp
View File

@@ -1,17 +1,17 @@
#pragma once
#include <cstdio>
#include <cstring>
#include <functional>
#include <list>
#include <memory>
#include <set>
#include <string>
#include <vector>
#include <functional>
#include "dictziplib.hpp"
const int MAX_MATCH_ITEM_PER_LIB = 100;
const int MAX_FUZZY_DISTANCE = 3; // at most MAX_FUZZY_DISTANCE-1 differences allowed when find similar words
const int MAX_MATCH_ITEM_PER_LIB=100;
const int MAX_FUZZY_DISTANCE= 3; // at most MAX_FUZZY_DISTANCE-1 differences allowed when find similar words
inline guint32 get_uint32(const gchar *addr)
{
@@ -25,202 +25,159 @@ inline void set_uint32(gchar *addr, guint32 val)
memcpy(addr, &val, sizeof(guint32));
}
struct cacheItem {
guint32 offset;
gchar *data;
// write code here to make it inline
cacheItem() { data = nullptr; }
~cacheItem() { g_free(data); }
guint32 offset;
gchar *data;
//write code here to make it inline
cacheItem() { data = nullptr;}
~cacheItem() { g_free(data); }
};
const int WORDDATA_CACHE_NUM = 10;
const int INVALID_INDEX = -100;
const int INVALID_INDEX=-100;
class DictBase
{
class DictBase {
public:
DictBase() {}
~DictBase()
{
DictBase() {}
~DictBase() {
if (dictfile)
fclose(dictfile);
}
DictBase(const DictBase &) = delete;
DictBase &operator=(const DictBase &) = delete;
gchar *GetWordData(guint32 idxitem_offset, guint32 idxitem_size);
bool containSearchData() const
{
DictBase(const DictBase&) = delete;
DictBase& operator=(const DictBase&) = delete;
gchar * GetWordData(guint32 idxitem_offset, guint32 idxitem_size);
bool containSearchData() const {
if (sametypesequence.empty())
return true;
return sametypesequence.find_first_of("mlgxty") != std::string::npos;
}
bool SearchData(std::vector<std::string> &SearchWords, guint32 idxitem_offset, guint32 idxitem_size, gchar *origin_data);
bool SearchData(std::vector<std::string> &SearchWords, guint32 idxitem_offset, guint32 idxitem_size, gchar *origin_data);
protected:
std::string sametypesequence;
FILE *dictfile = nullptr;
std::unique_ptr<DictData> dictdzfile;
std::string sametypesequence;
FILE *dictfile = nullptr;
std::unique_ptr<DictData> dictdzfile;
private:
cacheItem cache[WORDDATA_CACHE_NUM];
gint cache_cur = 0;
cacheItem cache[WORDDATA_CACHE_NUM];
gint cache_cur = 0;
};
// this structure contain all information about dictionary
//this structure contain all information about dictionary
struct DictInfo {
std::string ifo_file_name;
guint32 wordcount;
guint32 syn_wordcount;
std::string bookname;
std::string author;
std::string email;
std::string website;
std::string date;
std::string description;
guint32 index_file_size;
guint32 syn_file_size;
std::string sametypesequence;
std::string ifo_file_name;
guint32 wordcount;
std::string bookname;
std::string author;
std::string email;
std::string website;
std::string date;
std::string description;
guint32 index_file_size;
std::string sametypesequence;
bool load_from_ifo_file(const std::string &ifofilename, bool istreedict);
bool load_from_ifo_file(const std::string& ifofilename, bool istreedict);
};
class IIndexFile
{
class IIndexFile {
public:
guint32 wordentry_offset;
guint32 wordentry_size;
guint32 wordentry_offset;
guint32 wordentry_size;
virtual ~IIndexFile() {}
virtual bool load(const std::string &url, gulong wc, gulong fsize, bool verbose) = 0;
virtual const gchar *get_key(glong idx) = 0;
virtual void get_data(glong idx) = 0;
virtual const gchar *get_key_and_data(glong idx) = 0;
virtual bool lookup(const char *str, std::set<glong> &idxs, glong &next_idx) = 0;
virtual bool lookup(const char *str, std::set<glong> &idxs)
{
glong unused_next_idx;
return lookup(str, idxs, unused_next_idx);
};
virtual ~IIndexFile() {}
virtual bool load(const std::string& url, gulong wc, gulong fsize) = 0;
virtual const gchar *get_key(glong idx) = 0;
virtual void get_data(glong idx) = 0;
virtual const gchar *get_key_and_data(glong idx) = 0;
virtual bool lookup(const char *str, glong &idx) = 0;
};
class SynFile
{
class Dict : public DictBase {
public:
SynFile() {}
~SynFile() {}
bool load(const std::string &url, gulong wc);
bool lookup(const char *str, std::set<glong> &idxs, glong &next_idx);
bool lookup(const char *str, std::set<glong> &idxs);
const gchar *get_key(glong idx) { return synlist[idx]; }
Dict() {}
Dict(const Dict&) = delete;
Dict& operator=(const Dict&) = delete;
bool load(const std::string& ifofilename);
private:
MapFile synfile;
std::vector<gchar *> synlist;
};
gulong narticles() const { return wordcount; }
const std::string& dict_name() const { return bookname; }
const std::string& ifofilename() const { return ifo_file_name; }
class Dict : public DictBase
{
public:
Dict() {}
Dict(const Dict &) = delete;
Dict &operator=(const Dict &) = delete;
bool load(const std::string &ifofilename, bool verbose);
gulong narticles() const { return wordcount; }
const std::string &dict_name() const { return bookname; }
const std::string &ifofilename() const { return ifo_file_name; }
const gchar *get_key(glong index) { return idx_file->get_key(index); }
gchar *get_data(glong index)
{
const gchar *get_key(glong index) { return idx_file->get_key(index); }
gchar *get_data(glong index) {
idx_file->get_data(index);
return DictBase::GetWordData(idx_file->wordentry_offset, idx_file->wordentry_size);
}
void get_key_and_data(glong index, const gchar **key, guint32 *offset, guint32 *size)
{
void get_key_and_data(glong index, const gchar **key, guint32 *offset, guint32 *size) {
*key = idx_file->get_key_and_data(index);
*offset = idx_file->wordentry_offset;
*size = idx_file->wordentry_size;
}
bool Lookup(const char *str, std::set<glong> &idxs, glong &next_idx);
bool Lookup(const char *str, std::set<glong> &idxs)
{
glong unused_next_idx;
return Lookup(str, idxs, unused_next_idx);
}
bool Lookup(const char *str, glong &idx) { return idx_file->lookup(str, idx); }
bool LookupWithRule(GPatternSpec *pspec, glong *aIndex, int iBuffLen);
bool LookupWithRule(GPatternSpec *pspec, glong *aIndex, int iBuffLen);
private:
std::string ifo_file_name;
gulong wordcount;
std::string bookname;
private:
std::string ifo_file_name;
gulong wordcount;
gulong syn_wordcount;
std::string bookname;
std::unique_ptr<IIndexFile> idx_file;
std::unique_ptr<SynFile> syn_file;
bool load_ifofile(const std::string &ifofilename, gulong &idxfilesize);
std::unique_ptr<IIndexFile> idx_file;
bool load_ifofile(const std::string& ifofilename, gulong &idxfilesize);
};
class Libs
{
class Libs {
public:
Libs(std::function<void(void)> f = std::function<void(void)>())
{
Libs(std::function<void(void)> f = std::function<void(void)>()) {
progress_func = f;
iMaxFuzzyDistance = MAX_FUZZY_DISTANCE; // need to read from cfg.
iMaxFuzzyDistance = MAX_FUZZY_DISTANCE; //need to read from cfg.
}
void setVerbose(bool verbose) { verbose_ = verbose; }
void setFuzzy(bool fuzzy) { fuzzy_ = fuzzy; }
~Libs();
Libs(const Libs &) = delete;
Libs &operator=(const Libs &) = delete;
~Libs();
Libs(const Libs&) = delete;
Libs& operator=(const Libs&) = delete;
void load_dict(const std::string &url);
void load(const std::list<std::string> &dicts_dirs,
const std::list<std::string> &order_list,
const std::list<std::string> &disable_list);
glong narticles(int idict) const { return oLib[idict]->narticles(); }
const std::string &dict_name(int idict) const { return oLib[idict]->dict_name(); }
gint ndicts() const { return oLib.size(); }
void load_dict(const std::string& url);
void load(const std::list<std::string>& dicts_dirs,
const std::list<std::string>& order_list,
const std::list<std::string>& disable_list);
void reload(const std::list<std::string>& dicts_dirs,
const std::list<std::string>& order_list,
const std::list<std::string>& disable_list);
const gchar *poGetWord(glong iIndex, int iLib)
{
return oLib[iLib]->get_key(iIndex);
}
gchar *poGetWordData(glong iIndex, int iLib)
{
if (iIndex == INVALID_INDEX)
return nullptr;
return oLib[iLib]->get_data(iIndex);
}
bool LookupWord(const gchar *sWord, std::set<glong> &iWordIndices, int iLib)
{
return oLib[iLib]->Lookup(sWord, iWordIndices);
}
bool LookupSimilarWord(const gchar *sWord, std::set<glong> &iWordIndices, int iLib);
bool SimpleLookupWord(const gchar *sWord, std::set<glong> &iWordIndices, int iLib);
glong narticles(int idict) const { return oLib[idict]->narticles(); }
const std::string& dict_name(int idict) const { return oLib[idict]->dict_name(); }
gint ndicts() const { return oLib.size(); }
bool LookupWithFuzzy(const gchar *sWord, gchar *reslist[], gint reslist_size);
gint LookupWithRule(const gchar *sWord, gchar *reslist[]);
bool LookupData(const gchar *sWord, std::vector<gchar *> *reslist);
protected:
bool fuzzy_;
const gchar *poGetWord(glong iIndex, int iLib) {
return oLib[iLib]->get_key(iIndex);
}
gchar * poGetWordData(glong iIndex,int iLib) {
if (iIndex == INVALID_INDEX)
return nullptr;
return oLib[iLib]->get_data(iIndex);
}
const gchar *poGetCurrentWord(glong *iCurrent);
const gchar *poGetNextWord(const gchar *word, glong *iCurrent);
const gchar *poGetPreWord(glong *iCurrent);
bool LookupWord(const gchar* sWord, glong& iWordIndex, int iLib) {
return oLib[iLib]->Lookup(sWord, iWordIndex);
}
bool LookupSimilarWord(const gchar* sWord, glong & iWordIndex, int iLib);
bool SimpleLookupWord(const gchar* sWord, glong & iWordIndex, int iLib);
bool LookupWithFuzzy(const gchar *sWord, gchar *reslist[], gint reslist_size);
gint LookupWithRule(const gchar *sWord, gchar *reslist[]);
bool LookupData(const gchar *sWord, std::vector<gchar *> *reslist);
private:
std::vector<Dict *> oLib; // word Libs.
int iMaxFuzzyDistance;
std::vector<Dict *> oLib; // word Libs.
int iMaxFuzzyDistance;
std::function<void(void)> progress_func;
bool verbose_;
};
enum query_t {
qtSIMPLE,
qtREGEXP,
qtFUZZY,
qtDATA
qtSIMPLE, qtREGEXP, qtFUZZY, qtDATA
};
extern query_t analyze_query(const char *s, std::string& res);
extern query_t analyze_query(const char *s, std::string &res);

133
src/utils.cpp
View File

@@ -15,117 +15,78 @@
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
# include "config.h"
#endif
#include <algorithm>
#include <cstdio>
#include <cstdlib>
#include <glib.h>
#include <glib/gi18n.h>
#include <iomanip>
#include <sstream>
#include <cstdlib>
#include <cstdio>
#include <algorithm>
#include "utils.hpp"
std::string utf8_to_locale_ign_err(const std::string &utf8_str)
std::string utf8_to_locale_ign_err(const std::string& utf8_str)
{
std::string res;
std::string res;
const char *charset;
if (g_get_charset(&charset))
res = utf8_str;
else {
const char *charset;
if (g_get_charset(&charset))
res = utf8_str;
else {
gsize bytes_read, bytes_written;
glib::Error err;
glib::CharStr tmp(g_convert_with_fallback(utf8_str.c_str(), -1, charset, "UTF-8", nullptr,
&bytes_read, &bytes_written, get_addr(err)));
if (nullptr == get_impl(tmp)) {
fprintf(stderr, _("Can not convert %s to current locale.\n"), utf8_str.c_str());
fprintf(stderr, "%s\n", err->message);
exit(EXIT_FAILURE);
}
res = get_impl(tmp);
}
if (nullptr == get_impl(tmp)){
fprintf(stderr, _("Can not convert %s to current locale.\n"), utf8_str.c_str());
fprintf(stderr, "%s\n", err->message);
exit(EXIT_FAILURE);
}
res = get_impl(tmp);
}
return res;
return res;
}
static void __for_each_file(const std::string &dirname, const std::string &suff,
const std::list<std::string> &order_list, const std::list<std::string> &disable_list,
const std::function<void(const std::string &, bool)> &f)
static void __for_each_file(const std::string& dirname, const std::string& suff,
const std::list<std::string>& order_list, const std::list<std::string>& disable_list,
const std::function<void (const std::string&, bool)>& f)
{
GDir *dir = g_dir_open(dirname.c_str(), 0, nullptr);
GDir *dir = g_dir_open(dirname.c_str(), 0, nullptr);
if (dir) {
const gchar *filename;
const gchar *filename;
while ((filename = g_dir_read_name(dir)) != nullptr) {
const std::string fullfilename(dirname + G_DIR_SEPARATOR_S + filename);
if (g_file_test(fullfilename.c_str(), G_FILE_TEST_IS_DIR))
__for_each_file(fullfilename, suff, order_list, disable_list, f);
else if (g_str_has_suffix(filename, suff.c_str()) && std::find(order_list.begin(), order_list.end(), fullfilename) == order_list.end()) {
const bool disable = std::find(disable_list.begin(),
disable_list.end(),
fullfilename)
!= disable_list.end();
while ((filename = g_dir_read_name(dir))!=nullptr) {
const std::string fullfilename(dirname+G_DIR_SEPARATOR_S+filename);
if (g_file_test(fullfilename.c_str(), G_FILE_TEST_IS_DIR))
__for_each_file(fullfilename, suff, order_list, disable_list, f);
else if (g_str_has_suffix(filename, suff.c_str()) &&
std::find(order_list.begin(), order_list.end(),
fullfilename)==order_list.end()) {
const bool disable = std::find(disable_list.begin(),
disable_list.end(),
fullfilename)!=disable_list.end();
f(fullfilename, disable);
}
}
g_dir_close(dir);
}
}
}
g_dir_close(dir);
}
}
void for_each_file(const std::list<std::string> &dirs_list, const std::string &suff,
const std::list<std::string> &order_list, const std::list<std::string> &disable_list,
const std::function<void(const std::string &, bool)> &f)
{
for (const std::string &item : order_list) {
const bool disable = std::find(disable_list.begin(), disable_list.end(), item) != disable_list.end();
f(item, disable);
}
for (const std::string &item : dirs_list)
__for_each_file(item, suff, order_list, disable_list, f);
}
// based on https://stackoverflow.com/questions/7724448/simple-json-string-escape-for-c/33799784#33799784
std::string json_escape_string(const std::string &s)
void for_each_file(const std::list<std::string>& dirs_list, const std::string& suff,
const std::list<std::string>& order_list, const std::list<std::string>& disable_list,
const std::function<void (const std::string&, bool)>& f)
{
std::ostringstream o;
for (auto c = s.cbegin(); c != s.cend(); c++) {
switch (*c) {
case '"':
o << "\\\"";
break;
case '\\':
o << "\\\\";
break;
case '\b':
o << "\\b";
break;
case '\f':
o << "\\f";
break;
case '\n':
o << "\\n";
break;
case '\r':
o << "\\r";
break;
case '\t':
o << "\\t";
break;
default:
if ('\x00' <= *c && *c <= '\x1f') {
o << "\\u"
<< std::hex << std::setw(4) << std::setfill('0') << (int)*c;
} else {
o << *c;
}
}
}
return o.str();
for (const std::string & item : order_list) {
const bool disable = std::find(disable_list.begin(), disable_list.end(), item) != disable_list.end();
f(item, disable);
}
for (const std::string& item : dirs_list)
__for_each_file(item, suff, order_list, disable_list, f);
}

104
src/utils.hpp
View File

@@ -1,78 +1,68 @@
#pragma once
#include <cassert>
#include <cstddef>
#include <functional>
#include <glib.h>
#include <list>
#include <cassert>
#include <string>
#include <list>
#include <functional>
template <typename T, typename unref_res_t, void (*unref_res)(unref_res_t *)>
class ResourceWrapper
{
class ResourceWrapper {
public:
ResourceWrapper(T *p = nullptr)
: p_(p)
{
}
~ResourceWrapper() { free_resource(); }
ResourceWrapper(const ResourceWrapper &) = delete;
ResourceWrapper &operator=(const ResourceWrapper &) = delete;
T *operator->() const { return p_; }
bool operator!() const { return p_ == nullptr; }
const T &operator[](size_t idx) const
{
ResourceWrapper(T *p = nullptr) : p_(p) {}
~ResourceWrapper() { free_resource(); }
ResourceWrapper(const ResourceWrapper&) = delete;
ResourceWrapper& operator=(const ResourceWrapper&) = delete;
T *operator->() const { return p_; }
bool operator!() const { return p_ == nullptr; }
const T& operator[](size_t idx) const {
assert(p_ != nullptr);
return p_[idx];
}
void reset(T *newp)
{
if (p_ != newp) {
free_resource();
p_ = newp;
}
}
void reset(T *newp) {
if (p_ != newp) {
free_resource();
p_ = newp;
}
}
friend inline bool operator==(const ResourceWrapper &lhs, std::nullptr_t) noexcept
{
return !lhs.p_;
}
friend inline T *get_impl(const ResourceWrapper& rw) {
return rw.p_;
}
friend inline bool operator!=(const ResourceWrapper &lhs, std::nullptr_t) noexcept
{
return !!lhs.p_;
}
friend inline T *get_impl(const ResourceWrapper &rw)
{
return rw.p_;
}
friend inline T **get_addr(ResourceWrapper &rw)
{
return &rw.p_;
}
friend inline T **get_addr(ResourceWrapper& rw) {
return &rw.p_;
}
private:
T *p_;
T *p_;
void free_resource()
{
if (p_)
unref_res(p_);
void free_resource() { if (p_) unref_res(p_); }
// Helper for enabling 'if (sp)'
struct Tester {
Tester() {}
private:
void operator delete(void*);
};
public:
// enable 'if (sp)'
operator Tester*() const {
if (!*this)
return 0;
static Tester t;
return &t;
}
};
namespace glib
{
typedef ResourceWrapper<gchar, void, g_free> CharStr;
typedef ResourceWrapper<GError, GError, g_error_free> Error;
} // namespace glib
namespace glib {
typedef ResourceWrapper<gchar, void, g_free> CharStr;
typedef ResourceWrapper<GError, GError, g_error_free> Error;
}
extern std::string utf8_to_locale_ign_err(const std::string &utf8_str);
extern std::string utf8_to_locale_ign_err(const std::string& utf8_str);
extern void for_each_file(const std::list<std::string> &dirs_list, const std::string &suff,
const std::list<std::string> &order_list, const std::list<std::string> &disable_list,
const std::function<void(const std::string &, bool)> &f);
extern std::string json_escape_string(const std::string &str);
extern void for_each_file(const std::list<std::string>& dirs_list, const std::string& suff,
const std::list<std::string>& order_list, const std::list<std::string>& disable_list,
const std::function<void (const std::string&, bool)>& f);

27
tests/call_stardict_strcmp.cpp Normal file
View File

@@ -0,0 +1,27 @@
//g++ `pkg-config --cflags glib-2.0` call_stardict_strcmp.cpp `pkg-config --libs glib-2.0`
#include <glib.h>
#include <locale.h>
#include <cstdlib>
#include <cstring>
#include <iostream>
static inline gint stardict_strcmp(const gchar *s1, const gchar *s2)
{
const gint a = g_ascii_strcasecmp(s1, s2);
if (a == 0)
return strcmp(s1, s2);
else
return a;
}
int main()
{
setlocale(LC_ALL, "");
std::cin.sync_with_stdio(false);
std::string line1, line2;
while (std::getline(std::cin, line1) &&
std::getline(std::cin, line2)) {
std::cout << stardict_strcmp(line1.c_str(), line2.c_str()) << "\n";
}
return EXIT_SUCCESS;
}

42
tests/generate_strings_pairs.py Executable file
View File

@@ -0,0 +1,42 @@
#!/usr/bin/env python3
import random, sys
fname = "/home/evgeniy/projects/competitions/words/data/words.txt"
with open(fname, "r") as fin:
words = sorted(set([word.strip() for word in fin.readlines()]))
res = []
for i in range(0, len(words)):
max_idx = len(words) - 1
idx1 = random.randint(0, max_idx)
idx2 = random.randint(0, max_idx)
res.append((words[idx1], words[idx2]))
letters = "abcdefghijklmnopqrstuvwxyzабвгдеёжзийклмнопрстуфкцчщьъэюя"
letters += letters.upper()
letters += " \t!@#$%^&*()[]"
def gen_word(req_word_len):
max_idx = len(letters) - 1
res = ""
for i in range(0, req_word_len):
res += letters[random.randint(0, max_idx)]
return res
for i in range(0, 10000):
l1 = random.randint(1, 100)
l2 = random.randint(1, 100)
res.append((gen_word(l1), gen_word(l2)))
for i in range(0, 10000):
l1 = random.randint(1, 100)
res.append((gen_word(l1), gen_word(l1)))
for item in res:
print(item[0])
print(item[1])

0
tests/not-unix-newlines-ifo/russian/russian.dict
View File

0
tests/not-unix-newlines-ifo/russian/russian.idx
View File

9
tests/not-unix-newlines-ifo/russian/russian.ifo
View File

@@ -1,9 +0,0 @@
StarDict's dict ifo file
version=3.0.0
bookname=Russian-English Dictionary (ru-en)
wordcount=415144
idxfilesize=12344255
sametypesequence=h
synwordcount=1277580
author=Vuizur
description=

0
tests/not-unix-newlines-ifo/russian/russian.syn
View File

BIN
tests/rus-eng-stardict-2.4.2/1.xdxf.idx.oft
View File

Binary file not shown.

BIN
tests/stardict-test_multiple_results-2.4.2/test.dict
View File

Binary file not shown.

BIN
tests/stardict-test_multiple_results-2.4.2/test.idx
View File

Binary file not shown.

7
tests/stardict-test_multiple_results-2.4.2/test.ifo
View File

@@ -1,7 +0,0 @@
StarDict's dict ifo file
version=3.0.0
bookname=Test multiple results
wordcount=246
idxfilesize=5977
synwordcount=124
description=

BIN
tests/stardict-test_multiple_results-2.4.2/test.syn
View File

Binary file not shown.

BIN
tests/stardict-test_synonyms-2.4.2/test.dict.dz
View File

Binary file not shown.

BIN
tests/stardict-test_synonyms-2.4.2/test.idx
View File

Binary file not shown.

BIN
tests/stardict-test_synonyms-2.4.2/test.idx.oft
View File

Binary file not shown.

7
tests/stardict-test_synonyms-2.4.2/test.ifo
View File

@@ -1,7 +0,0 @@
StarDict's dict ifo file
version=2.4.2
bookname=Test synonyms
wordcount=2
synwordcount=2
idxfilesize=32
sametypesequence=m

BIN
tests/stardict-test_synonyms-2.4.2/test.syn
View File

Binary file not shown.

23
tests/stardict-test_synonyms-2.4.2/test.xml
View File

@@ -1,23 +0,0 @@
<?xml version="1.0" encoding="UTF-8" ?>
<stardict xmlns:xi="http://www.w3.org/2003/XInclude">
<info>
<version>2.4.2</version>
<bookname>Test synonyms</bookname>
<author></author>
<email></email>
<website></website>
<description></description>
<date></date>
<dicttype></dicttype>
</info>
<article><key>test</key><synonym>foo</synonym><synonym>bar</synonym>
<definition type="m">
<![CDATA[result of test]]>
</definition>
</article>
<article><key>testawordy</key>
<definition type="m">
<![CDATA[word that ends in y to test with fuzzy search in -ied]]>
</definition>
</article>
</stardict>

1363372
tests/stardict_strcmp_test_data.txt Normal file
View File

File diff suppressed because it is too large Load Diff

681686
tests/stardict_strcmp_test_data_cmp_exp.txt Normal file
View File

File diff suppressed because it is too large Load Diff

2
tests/t_datadir
View File

@@ -6,7 +6,7 @@ unset SDCV_PAGER
have=`"$PATH_TO_SDCV" --data-dir /tmp/bugagaga -l | wc -l`
#do not count header
have=$(($have-1))
ndicts=`find "${XDG_DATA_HOME:-$HOME/.local/share}"/stardict/dic -name "*.ifo" -print | wc -l`
ndicts=`find "${HOME}"/.stardict/dic -name "*.ifo" -print | wc -l`
#ndicts=$(($ndicts+1))
if [ $have -ne $ndicts ]; then
ndicts=$(($ndicts-1))

24
tests/t_exact
View File

@@ -1,24 +0,0 @@
#!/bin/sh
set -e
SDCV="$1"
TEST_DIR="$2"
unset SDCV_PAGER
test_word() {
WORD=$1
EXPECTED=$2
TAG=$3
RES=$($SDCV -e -n --data-dir "$TEST_DIR" -u "Test synonyms" $WORD | grep "$TAG")
if [ "$EXPECTED" != "$RES" ]; then
echo "synonym for $WORD should be '$EXPECTED' but was '$RES'"
exit 1
fi
}
test_word testawordies "Nothing similar to testawordies, sorry :(" "Nothing similar"
test_word testawordy "word that ends in y to test with fuzzy search in -ied" "fuzzy"
exit 0

32
tests/t_json
View File

@@ -1,32 +0,0 @@
#!/bin/sh
set -e
SDCV="$1"
TEST_DIR="$2"
unset SDCV_PAGER
unset STARDICT_DATA_DIR
test_json() {
EXPECTED=$(echo "$1" | jq 'sort')
shift
RESULT=$($SDCV "$@" | jq 'sort')
if [ "$EXPECTED" != "$RESULT" ]; then
echo "expected $EXPECTED but got $RESULT"
exit 1
fi
}
test_json '[{"name": "Russian-English Dictionary (ru-en)", "wordcount": "415144"},
{"name": "Test synonyms", "wordcount": "2"},
{"name": "Test multiple results", "wordcount": "246"},
{"name": "Sample 1 test dictionary", "wordcount": "1"},
{"name": "test_dict", "wordcount": "1"}]' -x -j -l -n --data-dir "$TEST_DIR"
test_json '[{"dict": "Test synonyms","word":"test","definition":"\u000aresult of test"}]' -x -j -n --data-dir "$TEST_DIR" foo
test_json '[]' -x -j -n --data-dir "$TEST_DIR" foobarbaaz
# Test multiple searches, with the first failing.
test_json '[][{"dict": "Test synonyms","word":"test","definition":"\u000aresult of test"}]' -x -j -n --data-dir "$TEST_DIR" foobarbaaz foo
exit 0

2
tests/t_list
View File

@@ -4,7 +4,7 @@ PATH_TO_SDCV="$1"
ndicts=`"$PATH_TO_SDCV" -l | wc -l`
ndicts=$(($ndicts-1))
ncom=`find /usr/share/stardict/dic -name "*.ifo" | wc -l`
nspe=`find "${XDG_DATA_HOME:-$HOME/.local/share}"/stardict/dic -name "*.ifo" | wc -l`
nspe=`find "${HOME}"/.stardict/dic -name "*.ifo" | wc -l`
nmy=$(($ncom+$nspe))
if [ $nmy -ne $ndicts ]; then

67
tests/t_multiple_results
View File

@@ -1,67 +0,0 @@
#!/bin/sh
set -e
SDCV="$1"
TEST_DIR="$2"
unset SDCV_PAGER
unset STARDICT_DATA_DIR
test_json() {
word="$1"
jq_cmp="$2"
result="$("$SDCV" --data-dir "$TEST_DIR" -exjn "$word" | sed 's|\\n|\\u000a|g')"
cmp_result="$(echo "$result" | jq "$jq_cmp")"
if [ "$cmp_result" != "true" ]; then
echo "expected '$jq_cmp' to return true, but $result didn't"
exit 1
fi
}
# Basic two-result search for the same headword.
test_json bark \
'. == [
{"dict":"Test multiple results","word":"bark","definition":"\u000aThe harsh sound made by a dog."},
{"dict":"Test multiple results","word":"bark","definition":"\u000aThe tough outer covering of trees and other woody plants."}
]'
# Multi-result search where one word exists as both a synyonym and a separate
# headword. This ensures that if there is a matching synyonym we don't skip the
# regular search.
test_json cat \
'. == [
{"dict":"Test multiple results","word":"cat","definition":"\u000aA cute animal which (rarely) barks."},
{"dict":"Test multiple results","word":"lion","definition":"\u000aA larger cat which might bite your head off."},
{"dict":"Test multiple results","word":"panther","definition":"\u000aI know very little about panthers, sorry."}
]'
# Many-result search for a word that matches 120 distinct headwords.
test_json many_headwords 'length == 120'
test_json many_headwords 'all(.word == "many_headwords")'
test_json many_headwords \
'to_entries | map(.value.definition == "\u000aDefinition for [many_headwords] entry #\(.key+1) (same headword).") | all'
# Many-result search for 120 words that have the same synonym.
test_json many_synonyms 'length == 120'
test_json many_synonyms \
'to_entries | map(.value.word == "many_synonyms-\(.key+101)") | all'
test_json many_synonyms \
'to_entries | map(.value.definition == "\u000aDefinition for [many_synonyms-\(.key+101)] (same synonym).") | all'
# Ensure that we don't return more than one result even if a word can be
# resolved in more than one way.
#
# Most well-formed dictionaries don't have entries like this (it basically
# requires you to have a dictionary where there is a synonym that is identical
# to a word's headword or multiple identical synyonym entries).
#
# This entry was created by creating extra synonyms with different names then
# modifying the .syn file manually.
test_json many_resolution_paths \
'. == [
{"dict":"Test multiple results","word":"many_resolution_paths",
"definition":"\u000aDefinition for [many_resolution_paths] headword (same word, multiple synonym entries)."}
]'
exit 0

18
tests/t_newlines_in_ifo
View File

@@ -1,18 +0,0 @@
#!/bin/sh
set -e
PATH_TO_SDCV="$1"
TEST_DIR="$2"
unset SDCV_PAGER
unset STARDICT_DATA_DIR
RES=$("$PATH_TO_SDCV" -n -x --data-dir="$TEST_DIR/not-unix-newlines-ifo" -l | tail -n 1)
if [ "$RES" = "Russian-English Dictionary (ru-en) 415144" ]; then
exit 0
else
echo "test failed, unexpected result: $RES" >&2
exit 1
fi

19
tests/t_only_data_dir
View File

@@ -1,19 +0,0 @@
#!/bin/sh
set -e
SDCV="$1"
TEST_DIR="$2"
unset SDCV_PAGER
unset STARDICT_DATA_DIR
DICTS=$($SDCV -x -n -l --data-dir "$TEST_DIR" | tail -n +2 | wc -l)
# the expected result:
ACTUAL_DICTS=$(find "$TEST_DIR" -name "*.ifo" | wc -l)
if [ $DICTS -ne $ACTUAL_DICTS ]; then
echo "number of dictionaries in $TEST_DIR should be $ACTUAL_DICTS but was $DICTS according to sdcv"
exit 1
fi
exit 0

22
tests/t_return_code
View File

@@ -1,22 +0,0 @@
#!/bin/sh
SDCV="$1"
TEST_DIR="$2"
unset SDCV_PAGER
test_return_code() {
WORD=$1
EXPECTED=$2
$SDCV -e -n --data-dir "$TEST_DIR" -u "Test synonyms" $WORD > /dev/null
RC=$?
if [ $RC -ne $EXPECTED ]; then
echo "Return code for $WORD should be '$EXPECTED' but was '$RC'"
exit 1
fi
}
test_return_code testawordy 0
test_return_code testawordies 2
exit 0

22
tests/t_synonyms
View File

@@ -1,22 +0,0 @@
#!/bin/sh
set -e
SDCV="$1"
TEST_DIR="$2"
unset SDCV_PAGER
test_word() {
WORD=$1
RES=$($SDCV -n --data-dir "$TEST_DIR" -u "Test synonyms" $WORD | grep result)
if [ "result of test" != "$RES" ]; then
echo "synonym for $WORD should be 'result of test' but was '$RES'"
exit 1
fi
}
test_word foo
test_word bar
test_word test
exit 0

6
tests/t_use
View File

@@ -5,8 +5,8 @@ set -e
PATH_TO_SDCV="$1"
TESTS_DIR="$2"
mkdir -p "${XDG_DATA_HOME:-$HOME/.local/share}"/stardict/dic
cp -R "${TESTS_DIR}/stardict-test_dict-2.4.2" "${XDG_DATA_HOME:-$HOME/.local/share}"/stardict/dic
mkdir -p "${HOME}"/.stardict/dic
cp -R "${TESTS_DIR}/stardict-test_dict-2.4.2" "${HOME}"/.stardict/dic
unset SDCV_PAGER
RES=`"$PATH_TO_SDCV" -n -u test_dict test | grep "test passed"`
@@ -15,6 +15,6 @@ if [ -z "$RES" ]; then
exit 1
fi
rm -fr "${XDG_DATA_HOME:-$HOME/.local/share}"/stardict/dic/stardict-test_dict-2.4.2
rm -fr "${HOME}"/.stardict/dic/stardict-test_dict-2.4.2
exit 0

5
tests/t_utf8input
View File

@@ -4,8 +4,9 @@ set -e
PATH_TO_SDCV="$1"
TESTS_DIR="$2"
mkdir -p "${XDG_DATA_HOME:-$HOME/.local/share}"/stardict/dic
cp -R "${TESTS_DIR}/rus-eng-stardict-2.4.2" "${XDG_DATA_HOME:-$HOME/.local/share}"/stardict/dic/
mkdir -p "${HOME}"/.stardict/dic
cp -R "${TESTS_DIR}/rus-eng-stardict-2.4.2" "${HOME}"/.stardict/dic/
unset SDCV_PAGER
export LANG=ru_RU.KOI8-R

10
tests/words_dic/gen_dic_from_words.py Executable file
View File

@@ -0,0 +1,10 @@
#!/usr/bin/env python3
import sys
with open(sys.argv[1], "r") as f:
with open(sys.argv[2], "w") as out:
words = set([word.strip() for word in f.readlines()])
for word in words:
out.write(word + "\n")
out.write(word + "\n")

1671705
tests/words_dic/stardict-words-2.4.2/words.dict Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
tests/words_dic/stardict-words-2.4.2/words.idx Normal file
View File

Binary file not shown.

BIN
tests/words_dic/stardict-words-2.4.2/words.idx.gz Normal file
View File

Binary file not shown.

BIN
tests/words_dic/stardict-words-2.4.2/words.idx.oft Normal file
View File

Binary file not shown.

7
tests/words_dic/stardict-words-2.4.2/words.ifo Normal file
View File

@@ -0,0 +1,7 @@
StarDict's dict ifo file
version=2.4.2
wordcount=1671704
idxfilesize=30235592
bookname=
date=2016.06.18
sametypesequence=x

3343408
tests/words_dic/words.dummy Normal file
View File

File diff suppressed because it is too large Load Diff