feat+refactor(lang+cli+report): Adds support for generating sources r…

…eports and support for the general way of getting translations.

- Adds support for the general way of getting translations with gettext;
- Adds some additional code checks with ruff;
- Moves CLI arguments check into argument parser;
- Adds support for generating source reports.
- Adds translations of the CLI help messages into Russian;
- Adds auto-tests for checking that the translation works;
- Adds auto-tests for checking creating reports with different translations.

Refs: #186.

.gitignore

@@ -33,3 +33,6 @@ src/codeplag/consts.py
 docker/base_ubuntu2004.dockerfile
 docker/test_ubuntu2004.dockerfile
 docker/ubuntu2004.dockerfile
+
+# Translation
+locales/**/*.mo

Makefile

@@ -1,4 +1,4 @@
-UTIL_VERSION            := 0.4.4
+UTIL_VERSION            := 0.4.5
 UTIL_NAME               := codeplag
 PWD                     := $(shell pwd)
 
@@ -82,7 +82,7 @@ man: substitute-sources
 					 --url "https://github.com/OSLL/code-plagiarism" \
 					 --output man/$(UTIL_NAME).1
 
-install: substitute-sources man
+install: substitute-sources man translate-compile
 	python3 -m pip install --root=/$(DESTDIR) .
 
 	@echo "Cleaning unnecessary files after Cython compilation"
@@ -97,8 +97,11 @@ install: substitute-sources man
 	install -D -m 0666 /dev/null $(DESTDIR)/$(CODEPLAG_LOG_PATH)
 	install -D -d -m 0755 $(DESTDIR)/$(LIB_PATH)
 
-	install -D -m 0666 src/templates/report_ru.templ $(DESTDIR)/$(LIB_PATH)/report_ru.templ
-	install -D -m 0666 src/templates/report_en.templ $(DESTDIR)/$(LIB_PATH)/report_en.templ
+	install -D -m 0666 src/templates/general.templ $(DESTDIR)/$(LIB_PATH)/general.templ
+	install -D -m 0666 src/templates/sources.templ $(DESTDIR)/$(LIB_PATH)/sources.templ
+
+	cp --recursive locales/translations/ $(DESTDIR)/$(LIB_PATH)/
+	find "$(DESTDIR)/$(LIB_PATH)/translations/" -type f -name '*.po' -exec rm --force {} +
 
 	if [ ! -f $(DESTDIR)/$(CONFIG_PATH) ]; then \
 		install -D -d -m 0755 $(DESTDIR)/etc/$(UTIL_NAME); \
@@ -168,7 +171,9 @@ reinstall: uninstall install
 todo-list: clean-all
 	@grep --color=auto -r -n 'TODO' ./* --exclude=Makefile --exclude-dir=docs
 
-help:
+help: help-general help-translate
+
+help-general:
 	@echo "Usage:"
 	@echo "  make [targets] [arguments]"
 	@echo
@@ -202,3 +207,4 @@ help:
 .PHONY: all test man
 
 include docker.mk
+include locales/i18n.mk

docker/test_ubuntu2004.dockerfile.in

@@ -2,6 +2,7 @@ FROM @BASE_DOCKER_TAG@
 
 ENV DEBIAN_FRONTEND=noninteractive
 
+RUN apt-get update
 RUN apt-get install -y debhelper
 RUN pip3 install pytest==7.4.0 pytest-mock==3.11.1 @PYTHON_BUILD_LIBS@
 RUN mkdir -p @LOGS_PATH@
@@ -12,6 +13,7 @@ ADD src/ /usr/src/@UTIL_NAME@/src
 ADD README.md /usr/src/@UTIL_NAME@/README.md
 ADD LICENSE /usr/src/@UTIL_NAME@/LICENSE
 ADD Makefile /usr/src/@UTIL_NAME@/Makefile
+ADD locales/ /usr/src/@UTIL_NAME@/locales
 ADD docker.mk /usr/src/@UTIL_NAME@/docker.mk
 ADD debian/ /usr/src/@UTIL_NAME@/debian
 

docker/ubuntu2004.dockerfile.in

@@ -6,6 +6,7 @@ ADD src/ /usr/src/@UTIL_NAME@/src
 ADD README.md /usr/src/@UTIL_NAME@/README.md
 ADD LICENSE /usr/src/@UTIL_NAME@/LICENSE
 ADD Makefile /usr/src/@UTIL_NAME@/Makefile
+ADD locales/i18n.mk /usr/src/@UTIL_NAME@/locales/i18n.mk
 ADD docker.mk /usr/src/@UTIL_NAME@/docker.mk
 ADD @DEBIAN_PACKAGES_PATH@ /usr/src/@UTIL_NAME@/@DEBIAN_PACKAGES_PATH@
 

docs/notebooks/utils.py

@@ -127,7 +127,6 @@ def plot_and_save_result(
         mean_times.append(summ / count)
 
     plt.figure(figsize=(12, 12), dpi=80)
-    # plt.plot(unique_count_lines, mean_times, label='Среднее')
 
     if trend == "linear":
         z = np.polyfit(unique_count_lines, mean_times, 1)

locales/babel.cfg

@@ -0,0 +1,2 @@
+[python: src/**.py]
+[jinja2: src/templates/*.templ]

locales/codeplag.pot

@@ -0,0 +1,296 @@
+# Translations template for codeplag.
+# Copyright (C) 2024 Codeplag Development Team
+# This file is distributed under the same license as the codeplag project.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2024.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: codeplag 0.4.5\n"
+"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n"
+"POT-Creation-Date: 2024-05-22 23:10+0300\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: Artyom Semidolin\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.14.0\n"
+
+#: src/codeplag/codeplagcli.py:44
+msgid "You cannot specify the same value multiple times. You provided '{values}'."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:61
+msgid "Directory '{path}' not found or not a directory."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:76
+msgid "File '{path}' not found or not a file."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:88
+msgid "Modifies and shows static settings of the '{util_name}' util."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:94
+msgid "Settings commands of the '{util_name}' util."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:105
+msgid "Manage the '{util_name}' util settings."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:112
+msgid "Path to the environment file with GitHub access token."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:118
+msgid "If defined, then saves reports about suspect works into provided path."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:127
+msgid "Extension of saved report files."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:134
+msgid "Show progress of searching plagiarism."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:141
+msgid ""
+"Threshold of analyzer which classifies two work as same. If this number "
+"is too large, such as 99, then completely matching jobs will be found. "
+"Otherwise, if this number is small, such as 50, then all work with "
+"minimal similarity will be found."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:155
+msgid "The language of help messages, generated reports, errors."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:162
+msgid "The maximum number of processes that can be used to compare works."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:172
+msgid "Show the '{util_name}' util settings."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:176
+msgid "Start searching similar works."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:182
+msgid "Absolute or relative path to a local directories with project files."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:194
+msgid "Absolute or relative path to files on a computer."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:201
+msgid ""
+"Choose one of the following modes of searching plagiarism. The "
+"'many_to_many' mode may require more free memory."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:212
+msgid ""
+"A regular expression for filtering checked works by name. Used with "
+"options 'directories', 'github-user' and 'github-project-folders'."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:221
+msgid "Ignore the threshold when checking of works."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:228
+msgid "Extension responsible for the analyzed programming language."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:238
+msgid "Searching in all branches."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:245
+msgid "A regular expression to filter searching repositories on GitHub."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:252
+msgid "URL to file in a GitHub repository."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:258
+msgid "GitHub organization/user name."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:265
+msgid "URL to a GitHub project folder."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:275
+msgid ""
+"Handling generated by the {util_name} reports as creating html report "
+"file or show it on console."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:283
+msgid "Report commands of the '{util_name}' util."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:294
+msgid "Generate general report from created some time ago report files."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:299
+msgid ""
+"Path to save generated report. If it's a directory, then create a file in"
+" it."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:309
+msgid "Type of the created report file."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:319
+msgid ""
+"Program help to find similar parts of source codes for the different "
+"languages."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:327
+msgid "Print current version number and exit."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:333
+msgid "Show debug messages."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:338
+msgid "Commands help."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:354
+msgid "No command is provided; please choose one from the available (--help)."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:369
+msgid "There is nothing to modify; please provide at least one argument."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:374
+msgid "The'repo-regexp' option requires the provided 'github-user' option."
+msgstr ""
+
+#: src/codeplag/codeplagcli.py:384
+msgid ""
+"The'path-regexp' option requires the provided 'directories', 'github-"
+"user', or 'github-project-folder' options."
+msgstr ""
+
+#: src/templates/general.templ:5 src/templates/sources.templ:5
+msgid "Comparative report"
+msgstr ""
+
+#: src/templates/general.templ:40
+msgid "Check results"
+msgstr ""
+
+#: src/templates/general.templ:44 src/templates/sources.templ:45
+msgid "General information"
+msgstr ""
+
+#: src/templates/general.templ:46
+msgid "Path"
+msgstr ""
+
+#: src/templates/general.templ:47
+msgid "Last modification date"
+msgstr ""
+
+#: src/templates/general.templ:48
+msgid "Check date"
+msgstr ""
+
+#: src/templates/general.templ:61
+msgid "Metrics information"
+msgstr ""
+
+#: src/templates/general.templ:63
+msgid "Metric"
+msgstr ""
+
+#: src/templates/general.templ:64
+msgid "Value"
+msgstr ""
+
+#: src/templates/general.templ:67
+msgid "Jaccard Coefficient"
+msgstr ""
+
+#: src/templates/general.templ:71
+msgid "Similarity of operators"
+msgstr ""
+
+#: src/templates/general.templ:75
+msgid "Similarity of keywords"
+msgstr ""
+
+#: src/templates/general.templ:79
+msgid "Similarity of literals"
+msgstr ""
+
+#: src/templates/general.templ:82
+msgid "Weighted average by fast metrics"
+msgstr ""
+
+#: src/templates/general.templ:85
+msgid "Similarity of structures"
+msgstr ""
+
+#: src/templates/general.templ:91
+msgid "Similar parts of the second program relative to the first"
+msgstr ""
+
+#: src/templates/general.templ:93 src/templates/general.templ:125
+msgid "Part of the first program"
+msgstr ""
+
+#: src/templates/general.templ:94 src/templates/general.templ:124
+msgid "Part of the second program"
+msgstr ""
+
+#: src/templates/general.templ:95 src/templates/general.templ:126
+#: src/templates/sources.templ:60
+msgid "Similarity"
+msgstr ""
+
+#: src/templates/general.templ:122
+msgid "Similar parts of the first program relative to the second"
+msgstr ""
+
+#: src/templates/sources.templ:41
+msgid "Verification results"
+msgstr ""
+
+#: src/templates/sources.templ:47
+msgid "The path to the file being checked"
+msgstr ""
+
+#: src/templates/sources.templ:55
+msgid "Similar parts of the programs"
+msgstr ""
+
+#: src/templates/sources.templ:57
+msgid "The name of a similar file"
+msgstr ""
+
+#: src/templates/sources.templ:58
+msgid "Part of the file that is being checked"
+msgstr ""
+
+#: src/templates/sources.templ:59
+msgid "Part of a similar file"
+msgstr ""
+