diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 54e5841..e5ba355 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -30,3 +30,8 @@ jobs: - name: Run tox run: tox + + - name: Upload coverage reports to Codecov + uses: codecov/codecov-action@v4.0.1 + with: + token: ${{ secrets.CODECOV_TOKEN }} \ No newline at end of file diff --git a/.readthedocs.yaml b/.readthedocs.yaml new file mode 100644 index 0000000..c1948b4 --- /dev/null +++ b/.readthedocs.yaml @@ -0,0 +1,9 @@ +version: "2" + +build: + os: "ubuntu-22.04" + tools: + python: "3.12" + +sphinx: + configuration: docs/source/conf.py \ No newline at end of file diff --git a/docs/history.rst b/CHANGELOG.rst similarity index 90% rename from docs/history.rst rename to CHANGELOG.rst index 1c4ef15..a9f5d85 100644 --- a/docs/history.rst +++ b/CHANGELOG.rst @@ -1,6 +1,18 @@ History ======= +0.5.0 (Unreleased) +------------------ + +* Added styles support +* Added comments support +* Added from_string +* Added iterate over a slice of captions +* Full refactor of the library without breaking changes +* Improved BOM support allowing to keep the BOM or remove it +* Deprecated read_buffer in favor of from_buffer +* Removed support for old versions of Python: 3.4, 3.5 and 3.6 + 0.4.6 (18-11-2020) ------------------ diff --git a/README.rst b/README.rst index 4a5aa23..a148839 100644 --- a/README.rst +++ b/README.rst @@ -4,8 +4,12 @@ webvtt-py .. image:: https://img.shields.io/pypi/v/webvtt-py.svg :target: https://pypi.python.org/pypi/webvtt-py -.. image:: https://travis-ci.org/glut23/webvtt-py.svg?branch=master - :target: https://travis-ci.org/glut23/webvtt-py +.. image:: https://img.shields.io/pypi/pyversions/webvtt-py.svg + :target: https://pypi.python.org/pypi/webvtt-py + +.. image:: https://img.shields.io/github/actions/workflow/status/glut23/webvtt-py/ci.yml + +.. image:: https://codecov.io/gh/glut23/webvtt-py/branch/master/graphs/badge.svg?branch=master .. image:: https://readthedocs.org/projects/webvtt-py/badge/?version=latest :target: http://webvtt-py.readthedocs.io/en/latest/?badge=latest @@ -13,8 +17,6 @@ webvtt-py ``webvtt-py`` is a Python module for reading/writing WebVTT_ caption files. It also features caption segmentation useful when captioning `HLS videos`_. -Requires Python 3.4+. - Documentation is available at http://webvtt-py.readthedocs.io. .. _`WebVTT`: http://dev.w3.org/html5/webvtt/ @@ -69,9 +71,10 @@ Supported formats: CLI --- Caption segmentation is also available from the command line: + :: - $ webvtt segment captions.vtt --output destination/directoy + $ webvtt segment captions.vtt --output output/path License ------- diff --git a/docs/Makefile b/docs/Makefile index 6838251..269cadc 100644 --- a/docs/Makefile +++ b/docs/Makefile @@ -1,230 +1,20 @@ -# Makefile for Sphinx documentation +# Minimal makefile for Sphinx documentation # -# You can set these variables from the command line. -SPHINXOPTS = -SPHINXBUILD = sphinx-build -PAPER = -BUILDDIR = _build +# You can set these variables from the command line, and also +# from the environment for the first two. +SPHINXOPTS ?= +SPHINXBUILD ?= sphinx-build +SOURCEDIR = source +BUILDDIR = build -# User-friendly check for sphinx-build -ifeq ($(shell which $(SPHINXBUILD) >/dev/null 2>&1; echo $$?), 1) - $(error The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed, then set the SPHINXBUILD environment variable to point to the full path of the '$(SPHINXBUILD)' executable. Alternatively you can add the directory with the executable to your PATH. If you don\'t have Sphinx installed, grab it from http://sphinx-doc.org/) -endif - -# Internal variables. -PAPEROPT_a4 = -D latex_paper_size=a4 -PAPEROPT_letter = -D latex_paper_size=letter -ALLSPHINXOPTS = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) . -# the i18n builder cannot share the environment and doctrees with the others -I18NSPHINXOPTS = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) . - -.PHONY: help +# Put it first so that "make" without argument is like "make help". help: - @echo "Please use \`make ' where is one of" - @echo " html to make standalone HTML files" - @echo " dirhtml to make HTML files named index.html in directories" - @echo " singlehtml to make a single large HTML file" - @echo " pickle to make pickle files" - @echo " json to make JSON files" - @echo " htmlhelp to make HTML files and a HTML help project" - @echo " qthelp to make HTML files and a qthelp project" - @echo " applehelp to make an Apple Help Book" - @echo " devhelp to make HTML files and a Devhelp project" - @echo " epub to make an epub" - @echo " epub3 to make an epub3" - @echo " latex to make LaTeX files, you can set PAPER=a4 or PAPER=letter" - @echo " latexpdf to make LaTeX files and run them through pdflatex" - @echo " latexpdfja to make LaTeX files and run them through platex/dvipdfmx" - @echo " text to make text files" - @echo " man to make manual pages" - @echo " texinfo to make Texinfo files" - @echo " info to make Texinfo files and run them through makeinfo" - @echo " gettext to make PO message catalogs" - @echo " changes to make an overview of all changed/added/deprecated items" - @echo " xml to make Docutils-native XML files" - @echo " pseudoxml to make pseudoxml-XML files for display purposes" - @echo " linkcheck to check all external links for integrity" - @echo " doctest to run all doctests embedded in the documentation (if enabled)" - @echo " coverage to run coverage check of the documentation (if enabled)" - @echo " dummy to check syntax errors of document sources" - -.PHONY: clean -clean: - rm -rf $(BUILDDIR)/* - -.PHONY: html -html: - $(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html - @echo - @echo "Build finished. The HTML pages are in $(BUILDDIR)/html." - -.PHONY: dirhtml -dirhtml: - $(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml - @echo - @echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml." - -.PHONY: singlehtml -singlehtml: - $(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml - @echo - @echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml." - -.PHONY: pickle -pickle: - $(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle - @echo - @echo "Build finished; now you can process the pickle files." - -.PHONY: json -json: - $(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json - @echo - @echo "Build finished; now you can process the JSON files." - -.PHONY: htmlhelp -htmlhelp: - $(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp - @echo - @echo "Build finished; now you can run HTML Help Workshop with the" \ - ".hhp project file in $(BUILDDIR)/htmlhelp." - -.PHONY: qthelp -qthelp: - $(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp - @echo - @echo "Build finished; now you can run "qcollectiongenerator" with the" \ - ".qhcp project file in $(BUILDDIR)/qthelp, like this:" - @echo "# qcollectiongenerator $(BUILDDIR)/qthelp/webvtt-py.qhcp" - @echo "To view the help file:" - @echo "# assistant -collectionFile $(BUILDDIR)/qthelp/webvtt-py.qhc" - -.PHONY: applehelp -applehelp: - $(SPHINXBUILD) -b applehelp $(ALLSPHINXOPTS) $(BUILDDIR)/applehelp - @echo - @echo "Build finished. The help book is in $(BUILDDIR)/applehelp." - @echo "N.B. You won't be able to view it unless you put it in" \ - "~/Library/Documentation/Help or install it in your application" \ - "bundle." - -.PHONY: devhelp -devhelp: - $(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp - @echo - @echo "Build finished." - @echo "To view the help file:" - @echo "# mkdir -p $$HOME/.local/share/devhelp/webvtt-py" - @echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/webvtt-py" - @echo "# devhelp" - -.PHONY: epub -epub: - $(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub - @echo - @echo "Build finished. The epub file is in $(BUILDDIR)/epub." - -.PHONY: epub3 -epub3: - $(SPHINXBUILD) -b epub3 $(ALLSPHINXOPTS) $(BUILDDIR)/epub3 - @echo - @echo "Build finished. The epub3 file is in $(BUILDDIR)/epub3." - -.PHONY: latex -latex: - $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex - @echo - @echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex." - @echo "Run \`make' in that directory to run these through (pdf)latex" \ - "(use \`make latexpdf' here to do that automatically)." - -.PHONY: latexpdf -latexpdf: - $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex - @echo "Running LaTeX files through pdflatex..." - $(MAKE) -C $(BUILDDIR)/latex all-pdf - @echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex." - -.PHONY: latexpdfja -latexpdfja: - $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex - @echo "Running LaTeX files through platex and dvipdfmx..." - $(MAKE) -C $(BUILDDIR)/latex all-pdf-ja - @echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex." - -.PHONY: text -text: - $(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text - @echo - @echo "Build finished. The text files are in $(BUILDDIR)/text." - -.PHONY: man -man: - $(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man - @echo - @echo "Build finished. The manual pages are in $(BUILDDIR)/man." - -.PHONY: texinfo -texinfo: - $(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo - @echo - @echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo." - @echo "Run \`make' in that directory to run these through makeinfo" \ - "(use \`make info' here to do that automatically)." - -.PHONY: info -info: - $(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo - @echo "Running Texinfo files through makeinfo..." - make -C $(BUILDDIR)/texinfo info - @echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo." - -.PHONY: gettext -gettext: - $(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale - @echo - @echo "Build finished. The message catalogs are in $(BUILDDIR)/locale." - -.PHONY: changes -changes: - $(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes - @echo - @echo "The overview file is in $(BUILDDIR)/changes." - -.PHONY: linkcheck -linkcheck: - $(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck - @echo - @echo "Link check complete; look for any errors in the above output " \ - "or in $(BUILDDIR)/linkcheck/output.txt." - -.PHONY: doctest -doctest: - $(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest - @echo "Testing of doctests in the sources finished, look at the " \ - "results in $(BUILDDIR)/doctest/output.txt." - -.PHONY: coverage -coverage: - $(SPHINXBUILD) -b coverage $(ALLSPHINXOPTS) $(BUILDDIR)/coverage - @echo "Testing of coverage in the sources finished, look at the " \ - "results in $(BUILDDIR)/coverage/python.txt." - -.PHONY: xml -xml: - $(SPHINXBUILD) -b xml $(ALLSPHINXOPTS) $(BUILDDIR)/xml - @echo - @echo "Build finished. The XML files are in $(BUILDDIR)/xml." + @$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) -.PHONY: pseudoxml -pseudoxml: - $(SPHINXBUILD) -b pseudoxml $(ALLSPHINXOPTS) $(BUILDDIR)/pseudoxml - @echo - @echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml." +.PHONY: help Makefile -.PHONY: dummy -dummy: - $(SPHINXBUILD) -b dummy $(ALLSPHINXOPTS) $(BUILDDIR)/dummy - @echo - @echo "Build finished. Dummy builder generates no files." +# Catch-all target: route all unknown targets to Sphinx using the new +# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS). +%: Makefile + @$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) \ No newline at end of file diff --git a/docs/conf.py b/docs/conf.py deleted file mode 100644 index af8a816..0000000 --- a/docs/conf.py +++ /dev/null @@ -1,297 +0,0 @@ -#!/usr/bin/env python3 -# -*- coding: utf-8 -*- -# -# webvtt-py documentation build configuration file, created by -# sphinx-quickstart on Sat May 21 12:44:33 2016. -# -# This file is execfile()d with the current directory set to its -# containing dir. -# -# Note that not all possible configuration values are present in this -# autogenerated file. -# -# All configuration values have a default; values that are commented out -# serve to show the default. - -import sys -import os - -# If extensions (or modules to document with autodoc) are in another directory, -# add these directories to sys.path here. If the directory is relative to the -# documentation root, use os.path.abspath to make it absolute, like shown here. -#sys.path.insert(0, os.path.abspath('.')) - -cwd = os.getcwd() -parent = os.path.dirname(cwd) -sys.path.append(parent) - -import webvtt - -# -- General configuration ------------------------------------------------ - -# If your documentation needs a minimal Sphinx version, state it here. -#needs_sphinx = '1.0' - -# Add any Sphinx extension module names here, as strings. They can be -# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom -# ones. -extensions = [ - 'sphinx.ext.autodoc', - 'sphinx.ext.doctest', - 'sphinx.ext.coverage', -] - -# Add any paths that contain templates here, relative to this directory. -templates_path = ['_templates'] - -# The suffix(es) of source filenames. -# You can specify multiple suffix as a list of string: -# source_suffix = ['.rst', '.md'] -source_suffix = '.rst' - -# The encoding of source files. -#source_encoding = 'utf-8-sig' - -# The master toctree document. -master_doc = 'index' - -# General information about the project. -project = 'webvtt-py' -copyright = '2016, Alejandro Mendez' -author = 'Alejandro Mendez' - -# The version info for the project you're documenting, acts as replacement for -# |version| and |release|, also used in various other places throughout the -# built documents. -# -# The short X.Y version. -version = '0.1.0' -# The full version, including alpha/beta/rc tags. -release = '0.1.0' - -# The language for content autogenerated by Sphinx. Refer to documentation -# for a list of supported languages. -# -# This is also used if you do content translation via gettext catalogs. -# Usually you set "language" from the command line for these cases. -language = None - -# There are two options for replacing |today|: either, you set today to some -# non-false value, then it is used: -#today = '' -# Else, today_fmt is used as the format for a strftime call. -#today_fmt = '%B %d, %Y' - -# List of patterns, relative to source directory, that match files and -# directories to ignore when looking for source files. -# This patterns also effect to html_static_path and html_extra_path -exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store'] - -# The reST default role (used for this markup: `text`) to use for all -# documents. -#default_role = None - -# If true, '()' will be appended to :func: etc. cross-reference text. -#add_function_parentheses = True - -# If true, the current module name will be prepended to all description -# unit titles (such as .. function::). -#add_module_names = True - -# If true, sectionauthor and moduleauthor directives will be shown in the -# output. They are ignored by default. -#show_authors = False - -# The name of the Pygments (syntax highlighting) style to use. -pygments_style = 'sphinx' - -# A list of ignored prefixes for module index sorting. -#modindex_common_prefix = [] - -# If true, keep warnings as "system message" paragraphs in the built documents. -#keep_warnings = False - -# If true, `todo` and `todoList` produce output, else they produce nothing. -todo_include_todos = False - - -# -- Options for HTML output ---------------------------------------------- - -# The theme to use for HTML and HTML Help pages. See the documentation for -# a list of builtin themes. -html_theme = 'sphinx_rtd_theme' - -# Theme options are theme-specific and customize the look and feel of a theme -# further. For a list of options available for each theme, see the -# documentation. -#html_theme_options = {} - -# Add any paths that contain custom themes here, relative to this directory. -#html_theme_path = [] - -# The name for this set of Sphinx documents. -# " v documentation" by default. -#html_title = 'webvtt-py v0.1.0' - -# A shorter title for the navigation bar. Default is the same as html_title. -#html_short_title = None - -# The name of an image file (relative to this directory) to place at the top -# of the sidebar. -#html_logo = None - -# The name of an image file (relative to this directory) to use as a favicon of -# the docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32 -# pixels large. -#html_favicon = None - -# Add any paths that contain custom static files (such as style sheets) here, -# relative to this directory. They are copied after the builtin static files, -# so a file named "default.css" will overwrite the builtin "default.css". -html_static_path = ['_static'] - -# Add any extra paths that contain custom files (such as robots.txt or -# .htaccess) here, relative to this directory. These files are copied -# directly to the root of the documentation. -#html_extra_path = [] - -# If not None, a 'Last updated on:' timestamp is inserted at every page -# bottom, using the given strftime format. -# The empty string is equivalent to '%b %d, %Y'. -#html_last_updated_fmt = None - -# If true, SmartyPants will be used to convert quotes and dashes to -# typographically correct entities. -#html_use_smartypants = True - -# Custom sidebar templates, maps document names to template names. -#html_sidebars = {} - -# Additional templates that should be rendered to pages, maps page names to -# template names. -#html_additional_pages = {} - -# If false, no module index is generated. -#html_domain_indices = True - -# If false, no index is generated. -#html_use_index = True - -# If true, the index is split into individual pages for each letter. -#html_split_index = False - -# If true, links to the reST sources are added to the pages. -#html_show_sourcelink = True - -# If true, "Created using Sphinx" is shown in the HTML footer. Default is True. -#html_show_sphinx = True - -# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True. -#html_show_copyright = True - -# If true, an OpenSearch description file will be output, and all pages will -# contain a tag referring to it. The value of this option must be the -# base URL from which the finished HTML is served. -#html_use_opensearch = '' - -# This is the file name suffix for HTML files (e.g. ".xhtml"). -#html_file_suffix = None - -# Language to be used for generating the HTML full-text search index. -# Sphinx supports the following languages: -# 'da', 'de', 'en', 'es', 'fi', 'fr', 'h', 'it', 'ja' -# 'nl', 'no', 'pt', 'ro', 'r', 'sv', 'tr', 'zh' -#html_search_language = 'en' - -# A dictionary with options for the search language support, empty by default. -# 'ja' uses this config value. -# 'zh' user can custom change `jieba` dictionary path. -#html_search_options = {'type': 'default'} - -# The name of a javascript file (relative to the configuration directory) that -# implements a search results scorer. If empty, the default will be used. -#html_search_scorer = 'scorer.js' - -# Output file base name for HTML help builder. -htmlhelp_basename = 'webvtt-pydoc' - -# -- Options for LaTeX output --------------------------------------------- - -latex_elements = { -# The paper size ('letterpaper' or 'a4paper'). -#'papersize': 'letterpaper', - -# The font size ('10pt', '11pt' or '12pt'). -#'pointsize': '10pt', - -# Additional stuff for the LaTeX preamble. -#'preamble': '', - -# Latex figure (float) alignment -#'figure_align': 'htbp', -} - -# Grouping the document tree into LaTeX files. List of tuples -# (source start file, target name, title, -# author, documentclass [howto, manual, or own class]). -latex_documents = [ - (master_doc, 'webvtt-py.tex', 'webvtt-py Documentation', - 'Alejandro Mendez', 'manual'), -] - -# The name of an image file (relative to this directory) to place at the top of -# the title page. -#latex_logo = None - -# For "manual" documents, if this is true, then toplevel headings are parts, -# not chapters. -#latex_use_parts = False - -# If true, show page references after internal links. -#latex_show_pagerefs = False - -# If true, show URL addresses after external links. -#latex_show_urls = False - -# Documents to append as an appendix to all manuals. -#latex_appendices = [] - -# If false, no module index is generated. -#latex_domain_indices = True - - -# -- Options for manual page output --------------------------------------- - -# One entry per manual page. List of tuples -# (source start file, name, description, authors, manual section). -man_pages = [ - (master_doc, 'webvtt-py', 'webvtt-py Documentation', - [author], 1) -] - -# If true, show URL addresses after external links. -#man_show_urls = False - - -# -- Options for Texinfo output ------------------------------------------- - -# Grouping the document tree into Texinfo files. List of tuples -# (source start file, target name, title, author, -# dir menu entry, description, category) -texinfo_documents = [ - (master_doc, 'webvtt-py', 'webvtt-py Documentation', - author, 'webvtt-py', 'One line description of project.', - 'Miscellaneous'), -] - -# Documents to append as an appendix to all manuals. -#texinfo_appendices = [] - -# If false, no module index is generated. -#texinfo_domain_indices = True - -# How to display URL addresses: 'footnote', 'no', or 'inline'. -#texinfo_show_urls = 'footnote' - -# If true, do not generate a @detailmenu in the "Top" node's menu. -#texinfo_no_detailmenu = False diff --git a/docs/make.bat b/docs/make.bat index 84d9650..fa98a78 100644 --- a/docs/make.bat +++ b/docs/make.bat @@ -1,64 +1,18 @@ @ECHO OFF +pushd %~dp0 + REM Command file for Sphinx documentation if "%SPHINXBUILD%" == "" ( set SPHINXBUILD=sphinx-build ) -set BUILDDIR=_build -set ALLSPHINXOPTS=-d %BUILDDIR%/doctrees %SPHINXOPTS% . -set I18NSPHINXOPTS=%SPHINXOPTS% . -if NOT "%PAPER%" == "" ( - set ALLSPHINXOPTS=-D latex_paper_size=%PAPER% %ALLSPHINXOPTS% - set I18NSPHINXOPTS=-D latex_paper_size=%PAPER% %I18NSPHINXOPTS% -) +set SOURCEDIR=source +set BUILDDIR=build if "%1" == "" goto help -if "%1" == "help" ( - :help - echo.Please use `make ^` where ^ is one of - echo. html to make standalone HTML files - echo. dirhtml to make HTML files named index.html in directories - echo. singlehtml to make a single large HTML file - echo. pickle to make pickle files - echo. json to make JSON files - echo. htmlhelp to make HTML files and a HTML help project - echo. qthelp to make HTML files and a qthelp project - echo. devhelp to make HTML files and a Devhelp project - echo. epub to make an epub - echo. epub3 to make an epub3 - echo. latex to make LaTeX files, you can set PAPER=a4 or PAPER=letter - echo. text to make text files - echo. man to make manual pages - echo. texinfo to make Texinfo files - echo. gettext to make PO message catalogs - echo. changes to make an overview over all changed/added/deprecated items - echo. xml to make Docutils-native XML files - echo. pseudoxml to make pseudoxml-XML files for display purposes - echo. linkcheck to check all external links for integrity - echo. doctest to run all doctests embedded in the documentation if enabled - echo. coverage to run coverage check of the documentation if enabled - echo. dummy to check syntax errors of document sources - goto end -) - -if "%1" == "clean" ( - for /d %%i in (%BUILDDIR%\*) do rmdir /q /s %%i - del /q /s %BUILDDIR%\* - goto end -) - - -REM Check if sphinx-build is available and fallback to Python version if any -%SPHINXBUILD% 1>NUL 2>NUL -if errorlevel 9009 goto sphinx_python -goto sphinx_ok - -:sphinx_python - -set SPHINXBUILD=python -m sphinx.__init__ -%SPHINXBUILD% 2> nul +%SPHINXBUILD% >NUL 2>NUL if errorlevel 9009 ( echo. echo.The 'sphinx-build' command was not found. Make sure you have Sphinx @@ -71,211 +25,11 @@ if errorlevel 9009 ( exit /b 1 ) -:sphinx_ok +%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O% +goto end - -if "%1" == "html" ( - %SPHINXBUILD% -b html %ALLSPHINXOPTS% %BUILDDIR%/html - if errorlevel 1 exit /b 1 - echo. - echo.Build finished. The HTML pages are in %BUILDDIR%/html. - goto end -) - -if "%1" == "dirhtml" ( - %SPHINXBUILD% -b dirhtml %ALLSPHINXOPTS% %BUILDDIR%/dirhtml - if errorlevel 1 exit /b 1 - echo. - echo.Build finished. The HTML pages are in %BUILDDIR%/dirhtml. - goto end -) - -if "%1" == "singlehtml" ( - %SPHINXBUILD% -b singlehtml %ALLSPHINXOPTS% %BUILDDIR%/singlehtml - if errorlevel 1 exit /b 1 - echo. - echo.Build finished. The HTML pages are in %BUILDDIR%/singlehtml. - goto end -) - -if "%1" == "pickle" ( - %SPHINXBUILD% -b pickle %ALLSPHINXOPTS% %BUILDDIR%/pickle - if errorlevel 1 exit /b 1 - echo. - echo.Build finished; now you can process the pickle files. - goto end -) - -if "%1" == "json" ( - %SPHINXBUILD% -b json %ALLSPHINXOPTS% %BUILDDIR%/json - if errorlevel 1 exit /b 1 - echo. - echo.Build finished; now you can process the JSON files. - goto end -) - -if "%1" == "htmlhelp" ( - %SPHINXBUILD% -b htmlhelp %ALLSPHINXOPTS% %BUILDDIR%/htmlhelp - if errorlevel 1 exit /b 1 - echo. - echo.Build finished; now you can run HTML Help Workshop with the ^ -.hhp project file in %BUILDDIR%/htmlhelp. - goto end -) - -if "%1" == "qthelp" ( - %SPHINXBUILD% -b qthelp %ALLSPHINXOPTS% %BUILDDIR%/qthelp - if errorlevel 1 exit /b 1 - echo. - echo.Build finished; now you can run "qcollectiongenerator" with the ^ -.qhcp project file in %BUILDDIR%/qthelp, like this: - echo.^> qcollectiongenerator %BUILDDIR%\qthelp\webvtt-py.qhcp - echo.To view the help file: - echo.^> assistant -collectionFile %BUILDDIR%\qthelp\webvtt-py.ghc - goto end -) - -if "%1" == "devhelp" ( - %SPHINXBUILD% -b devhelp %ALLSPHINXOPTS% %BUILDDIR%/devhelp - if errorlevel 1 exit /b 1 - echo. - echo.Build finished. - goto end -) - -if "%1" == "epub" ( - %SPHINXBUILD% -b epub %ALLSPHINXOPTS% %BUILDDIR%/epub - if errorlevel 1 exit /b 1 - echo. - echo.Build finished. The epub file is in %BUILDDIR%/epub. - goto end -) - -if "%1" == "epub3" ( - %SPHINXBUILD% -b epub3 %ALLSPHINXOPTS% %BUILDDIR%/epub3 - if errorlevel 1 exit /b 1 - echo. - echo.Build finished. The epub3 file is in %BUILDDIR%/epub3. - goto end -) - -if "%1" == "latex" ( - %SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex - if errorlevel 1 exit /b 1 - echo. - echo.Build finished; the LaTeX files are in %BUILDDIR%/latex. - goto end -) - -if "%1" == "latexpdf" ( - %SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex - cd %BUILDDIR%/latex - make all-pdf - cd %~dp0 - echo. - echo.Build finished; the PDF files are in %BUILDDIR%/latex. - goto end -) - -if "%1" == "latexpdfja" ( - %SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex - cd %BUILDDIR%/latex - make all-pdf-ja - cd %~dp0 - echo. - echo.Build finished; the PDF files are in %BUILDDIR%/latex. - goto end -) - -if "%1" == "text" ( - %SPHINXBUILD% -b text %ALLSPHINXOPTS% %BUILDDIR%/text - if errorlevel 1 exit /b 1 - echo. - echo.Build finished. The text files are in %BUILDDIR%/text. - goto end -) - -if "%1" == "man" ( - %SPHINXBUILD% -b man %ALLSPHINXOPTS% %BUILDDIR%/man - if errorlevel 1 exit /b 1 - echo. - echo.Build finished. The manual pages are in %BUILDDIR%/man. - goto end -) - -if "%1" == "texinfo" ( - %SPHINXBUILD% -b texinfo %ALLSPHINXOPTS% %BUILDDIR%/texinfo - if errorlevel 1 exit /b 1 - echo. - echo.Build finished. The Texinfo files are in %BUILDDIR%/texinfo. - goto end -) - -if "%1" == "gettext" ( - %SPHINXBUILD% -b gettext %I18NSPHINXOPTS% %BUILDDIR%/locale - if errorlevel 1 exit /b 1 - echo. - echo.Build finished. The message catalogs are in %BUILDDIR%/locale. - goto end -) - -if "%1" == "changes" ( - %SPHINXBUILD% -b changes %ALLSPHINXOPTS% %BUILDDIR%/changes - if errorlevel 1 exit /b 1 - echo. - echo.The overview file is in %BUILDDIR%/changes. - goto end -) - -if "%1" == "linkcheck" ( - %SPHINXBUILD% -b linkcheck %ALLSPHINXOPTS% %BUILDDIR%/linkcheck - if errorlevel 1 exit /b 1 - echo. - echo.Link check complete; look for any errors in the above output ^ -or in %BUILDDIR%/linkcheck/output.txt. - goto end -) - -if "%1" == "doctest" ( - %SPHINXBUILD% -b doctest %ALLSPHINXOPTS% %BUILDDIR%/doctest - if errorlevel 1 exit /b 1 - echo. - echo.Testing of doctests in the sources finished, look at the ^ -results in %BUILDDIR%/doctest/output.txt. - goto end -) - -if "%1" == "coverage" ( - %SPHINXBUILD% -b coverage %ALLSPHINXOPTS% %BUILDDIR%/coverage - if errorlevel 1 exit /b 1 - echo. - echo.Testing of coverage in the sources finished, look at the ^ -results in %BUILDDIR%/coverage/python.txt. - goto end -) - -if "%1" == "xml" ( - %SPHINXBUILD% -b xml %ALLSPHINXOPTS% %BUILDDIR%/xml - if errorlevel 1 exit /b 1 - echo. - echo.Build finished. The XML files are in %BUILDDIR%/xml. - goto end -) - -if "%1" == "pseudoxml" ( - %SPHINXBUILD% -b pseudoxml %ALLSPHINXOPTS% %BUILDDIR%/pseudoxml - if errorlevel 1 exit /b 1 - echo. - echo.Build finished. The pseudo-XML files are in %BUILDDIR%/pseudoxml. - goto end -) - -if "%1" == "dummy" ( - %SPHINXBUILD% -b dummy %ALLSPHINXOPTS% %BUILDDIR%/dummy - if errorlevel 1 exit /b 1 - echo. - echo.Build finished. Dummy builder generates no files. - goto end -) +:help +%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O% :end +popd \ No newline at end of file diff --git a/docs/requirements.txt b/docs/requirements.txt index 993b547..41c5fce 100644 --- a/docs/requirements.txt +++ b/docs/requirements.txt @@ -1 +1,2 @@ -sphinx-rtd-theme==0.1.9 \ No newline at end of file +sphinx==7.3.7 +sphinx-rtd-theme==2.0.0 \ No newline at end of file diff --git a/docs/source/conf.py b/docs/source/conf.py new file mode 100644 index 0000000..8bb54f5 --- /dev/null +++ b/docs/source/conf.py @@ -0,0 +1,45 @@ +# Configuration file for the Sphinx documentation builder. + +import sys +from pathlib import Path + +# Add parent dir to path +parent_directory = Path(__file__).resolve().parent +sys.path.append(str(parent_directory)) + +from datetime import date +import webvtt # noqa + +# -- Project information + +project = 'webvtt-py' +copyright = f'2016-{date.today().year}, {webvtt.__author__}' +author = webvtt.__author__ + +release = webvtt.__version__ +version = webvtt.__version__ + +# -- General configuration + +extensions = [ + 'sphinx.ext.duration', + 'sphinx.ext.doctest', + 'sphinx.ext.autodoc', + 'sphinx.ext.autosummary', + 'sphinx.ext.intersphinx', +] + +intersphinx_mapping = { + 'python': ('https://docs.python.org/3/', None), + 'sphinx': ('https://www.sphinx-doc.org/en/master/', None), +} +intersphinx_disabled_domains = ['std'] + +templates_path = ['_templates'] + +# -- Options for HTML output + +html_theme = 'sphinx_rtd_theme' + +# -- Options for EPUB output +epub_show_urls = 'footnote' \ No newline at end of file diff --git a/docs/source/history.rst b/docs/source/history.rst new file mode 100644 index 0000000..6f90edd --- /dev/null +++ b/docs/source/history.rst @@ -0,0 +1 @@ +.. include:: ../../CHANGELOG.rst \ No newline at end of file diff --git a/docs/index.rst b/docs/source/index.rst similarity index 100% rename from docs/index.rst rename to docs/source/index.rst diff --git a/docs/package.rst b/docs/source/package.rst similarity index 100% rename from docs/package.rst rename to docs/source/package.rst diff --git a/docs/quickstart.rst b/docs/source/quickstart.rst similarity index 91% rename from docs/quickstart.rst rename to docs/source/quickstart.rst index 111a623..855e7cd 100644 --- a/docs/quickstart.rst +++ b/docs/source/quickstart.rst @@ -19,7 +19,7 @@ To install with easy_install: Requirements ------------ -This module requires Python 3.4+. +This module requires Python 3.7+. Source code diff --git a/docs/source/usage.rst b/docs/source/usage.rst new file mode 100644 index 0000000..58ad3f8 --- /dev/null +++ b/docs/source/usage.rst @@ -0,0 +1,362 @@ +Usage +===== + +Reading WebVTT caption files +---------------------------- + +.. code-block:: python + + import webvtt + + # we can iterate over the captions + for caption in webvtt.read('captions.vtt'): + print(caption.start) # start timestamp in text format + print(caption.end) # end timestamp in text format + print(caption.text) # caption text + + # you can also iterate over the lines of a particular caption + for line in vtt[0].lines: + print(line) + + # caption text is returned clean without class tags + # we can access the raw text of a caption with raw_text + >>> vtt[0].text + 'This is a caption text' + >>> vtt[0].raw_text + 'This is a caption text' + + # caption identifiers + >>> vtt[0].identifier + 'chapter 1' + + +Reading WebVTT caption files from a file-like object +---------------------------------------------------- + +.. code-block:: python + + import webvtt + import requests + from io import StringIO + + payload = requests.get('http://subtitles.com/1234.vtt').text() + buffer = StringIO(payload) + + for caption in webvtt.from_buffer(buffer): + print(caption.start) + print(caption.end) + print(caption.text) + + +Reading WebVTT captions from a string +------------------------------------- + +.. code-block:: python + + import webvtt + import textwrap + + vtt = webvtt.from_string(textwrap.dedent(""" + WEBVTT + + 00:00:00.500 --> 00:00:07.000 + Caption #1 + + 00:00:07.000 --> 00:00:11.890 + Caption #2 line 1 + Caption #2 line 2 + + 00:00:11.890 --> 00:00:16.320 + Caption #3 + """).strip() + ) + + for caption in vtt: + print(caption.start) + print(caption.end) + print(caption.text) + + +Iterate a slice of captions +--------------------------- + +.. code-block:: python + + import webvtt + + vtt = webvtt.read('captions.vtt') + for caption in vtt.iter_slice(start='00:00:11.000', + end='00:00:27.000' + ) + print(caption.start) + print(caption.end) + print(caption.text) + + +Creating captions +----------------- + +.. code-block:: python + + from webvtt import WebVTT, Caption + + vtt = WebVTT() + + # creating a caption with a list of lines + caption = Caption( + '00:00:00.500', + '00:00:07.000', + ['Caption line 1', 'Caption line 2'] + ) + + # an identifier can be assigned + caption.identifier = 'chapter 1' + + # adding a caption + vtt.captions.append(caption) + + # creating another caption with a text + caption = Caption( + '00:00:07.000', + '00:00:11.890', + 'Caption line 1\nCaption line 2' + ) + + vtt.captions.append(caption) + + +Manipulating captions +--------------------- + +.. code-block:: python + + import webvtt + + vtt = webvtt.read('captions.vtt') + + # update start timestamp + vtt[0].start = '00:00:01.250' + + # update end timestamp + vtt[0].end = '00:00:03.890' + + # update caption text + vtt[0].text = 'New caption text' + + # delete a caption + del vtt.captions[2] + + +Saving captions +--------------- + +.. code-block:: python + + import webvtt + + vtt = webvtt.read('captions.vtt') + + # save to the same file + vtt.save() + + # save to a different file + vtt.save('new_captions.vtt') + + # you can save to a file path + vtt.save('other/folder/new_captions') + + # if there is a filename present in the object we can target a folder + vtt.save('other/folder) + + # write to an opened file + with open('other_captions.vtt', 'w') as f: + vtt.write(f) + + +Retrieving WebVTT formatted captions +------------------------------------ + +WebVTT content can be retrieved without an output file: + +.. code-block:: python + + import webvtt + + vtt = webvtt.read('captions.vtt') + + # print the content in WebVTT format + print(vtt.content) + + +Converting captions +------------------- + +You can read captions from the following formats: + +* SubRip (.srt) +* YouTube SBV (.sbv) + +.. code-block:: python + + import webvtt + + # read captions from SRT format + vtt = webvtt.from_srt('captions.srt') + + # save the captions in WebVTT format + vtt.save() + + # the conversion can be done chaining the method calls + webvtt.from_srt('captions.srt').save() + + # the same for SBV format + vtt = webvtt.from_sbv('captions.sbv') + +Convert WebVTT captions to other formats: + +* SubRip (.srt) + +.. code-block:: python + + import webvtt + + # save in SRT format + vtt = webvtt.read('captions.vtt') + vtt.save_as_srt() + + # write to an opened file in SRT format + with open('captions.srt', 'w') as f: + vtt.write(f, format='srt') + + +WebVTT files with Byte Order Mark (BOM) +--------------------------------------- + +When the WebVTT file has BOM, saving it will keep the BOM: + +.. code-block:: python + + import webvtt + + vtt = webvtt.read('captions_with_bom.vtt') + + # saved file keeps the BOM + vtt.save() + + +Add a BOM to a file without it: + +.. code-block:: python + + import webvtt + + vtt = webvtt.read('captions_without_bom.vtt', + add_bom=True + ) + + # saved file has BOM + vtt.save() + + +Remove the BOM from a file: + +.. code-block:: python + + import webvtt + + vtt = webvtt.read('captions_with_bom.vtt') + + # saved file does not have BOM + vtt.save(add_bom=False) + + +Save file with a different encoding: + +.. code-block:: python + + import webvtt + + vtt = webvtt.read('captions.vtt') + + vtt.save(encoding='utf-32-le') + + # save in different encoding with BOM + vtt.save(encoding='utf-32-le', + add_bom=True + ) + + + +WebVTT Styles +------------- + +.. code-block:: python + + import webvtt + + vtt = webvtt.read('captions.vtt') + + for style in vtt.styles: + print(style.text) + + # retrieve list of lines + print(style.lines) + + +Adding styles: + +.. code-block:: python + + import webvtt + + vtt = webvtt.read('captions.vtt') + + vtt.styles.append( + webvtt.Style('::cue(b) {\n color: peachpuff;\n}') + ) + # list of lines is supported + vtt.styles.append( + webvtt.Style(['::cue(b) {', + ' color: peachpuff;', + '}' + ]) + ) + + +Updating styles: + +.. code-block:: python + + import webvtt + + vtt = webvtt.read('captions.vtt') + + vtt.styles[0].lines[1] = ' color: papayawhip;' + + +WebVTT Comments +--------------- + +Comments can be added or retrieved from different items: + +.. code-block:: python + + import webvtt + + vtt = webvtt.read('captions.vtt') + + # comments from the top of the file + print(vtt.header_comments) + + # comments from the bottom of the file + print(vtt.footer_comments) + + # comments in a style + print(vtt.styles[0].comments) + + # comments in a caption + print(vtt.captions[0].comments) + + # comments are just a list of strings + vtt.captions[5].comments.append('caption for review') + diff --git a/docs/usage.rst b/docs/usage.rst deleted file mode 100644 index 491bab9..0000000 --- a/docs/usage.rst +++ /dev/null @@ -1,171 +0,0 @@ -Usage -===== - -Reading WebVTT caption files ----------------------------- - -.. code-block:: python - - import webvtt - - # we can iterate over the captions - for caption in webvtt.read('captions.vtt'): - print(caption.start) # start timestamp in text format - print(caption.end) # end timestamp in text format - print(caption.text) # caption text - - # you can also iterate over the lines of a particular caption - for line in vtt[0].lines: - print(line) - - # caption text is returned clean without class tags - # we can access the raw text of a caption with raw_text - >>> vtt[0].text - 'This is a caption text' - >>> vtt[0].raw_text - 'This is a caption text' - - # caption identifiers - >>> vtt[0].identifier - 'crédit de transcription' - - -Reading WebVTT caption files from file-like object --------------------------------------------------- - -.. code-block:: python - - import webvtt - import requests - from io import StringIO - - payload = requests.get('http://subtitles.com/1234.vtt').text() - buffer = StringIO(payload) - - for caption in webvtt.read_buffer(buffer): - print(caption.start) - print(caption.end) - print(caption.text) - - -Creating captions ------------------ - -.. code-block:: python - - from webvtt import WebVTT, Caption - - vtt = WebVTT() - - # creating a caption with a list of lines - caption = Caption( - '00:00:00.500', - '00:00:07.000', - ['Caption line 1', 'Caption line 2'] - ) - - # adding a caption - vtt.captions.append(caption) - - # creating another caption with a text - caption = Caption( - '00:00:07.000', - '00:00:11.890', - 'Caption line 1\nCaption line 2' - ) - - vtt.captions.append(caption) - - -Manipulating captions ---------------------- - -.. code-block:: python - - import webvtt - - vtt = webvtt.read('captions.vtt') - - # update start timestamp - vtt[0].start = '00:00:01.250' - - # update end timestamp - vtt[0].end = '00:00:03.890' - - # update caption text - vtt[0].text = 'My caption text' - - # delete a caption - del vtt.captions[2] - - -Saving captions ---------------- - -.. code-block:: python - - import webvtt - - vtt = webvtt.read('captions.vtt') - - # save to original file - vtt.save() - - # save to a different file - vtt.save('my_captions.vtt') - - # write to opened file - with open('my_captions.vtt', 'w') as fd: - vtt.write(fd) - - -Fetching WebVTT formatted Captions ------------------------------------- - -WebVTT formatted captions content can be obtained without having to create an output file. - -.. code-block:: python - - import webvtt - - vtt = webvtt.read('captions.vtt') - - # Print the captions formatted in webvtt - print(vtt.content) - - -Converting captions -------------------- - -You can read captions from the following formats: - -* SubRip (.srt) -* YouTube SBV (.sbv) - -.. code-block:: python - - import webvtt - - # to read from a different format use the method from_ followed by - # the extension. - vtt = webvtt.from_sbv('captions.sbv') - vtt.save() - - # if we just want to convert the file we can do this in one line - webvtt.from_sbv('captions.sbv').save() - -Also we can convert WebVTT to other formats: - -* SubRip (.srt) - -.. code-block:: python - - import webvtt - - # save in SRT format - vtt = webvtt.read('captions.vtt') - vtt.save_as_srt() - - # write to opened file in SRT format - with open('my_captions.srt', 'w') as fd: - vtt.write(fd, format='srt') diff --git a/setup.py b/setup.py index 6bae26d..851f8a4 100644 --- a/setup.py +++ b/setup.py @@ -5,11 +5,12 @@ from setuptools import setup, find_packages -version = ( +version, author, author_email = ( re.search( - r'__version__ = \'(.*?)\'', + rf'__{name}__ = \'(.*?)\'', pathlib.Path('webvtt/__init__.py').read_text() ).group(1) + for name in ('version', 'author', 'author_email') ) setup( @@ -17,8 +18,8 @@ version=version, description='WebVTT reader, writer and segmenter', long_description=pathlib.Path('README.rst').read_text(), - author='Alejandro Mendez', - author_email='amendez23@gmail.com', + author=author, + author_email=author_email, url='https://github.com/glut23/webvtt-py', packages=find_packages('.', exclude=['tests']), include_package_data=True, @@ -30,7 +31,7 @@ license='MIT', python_requires='>=3.7', classifiers=[ - 'Development Status :: 3 - Alpha', + 'Development Status :: 4 - Beta', 'Intended Audience :: Developers', 'License :: OSI Approved :: MIT License', 'Programming Language :: Python', @@ -38,6 +39,9 @@ 'Programming Language :: Python :: 3.7', 'Programming Language :: Python :: 3.8', 'Programming Language :: Python :: 3.9', + 'Programming Language :: Python :: 3.10', + 'Programming Language :: Python :: 3.11', + 'Programming Language :: Python :: 3.12', 'Operating System :: OS Independent', 'Topic :: Software Development :: Libraries :: Python Modules', ], diff --git a/tests/test_webvtt.py b/tests/test_webvtt.py index 3111e2f..ccdc5d1 100644 --- a/tests/test_webvtt.py +++ b/tests/test_webvtt.py @@ -17,7 +17,7 @@ class TestWebVTT(unittest.TestCase): def test_from_string(self): - vtt = webvtt.WebVTT.from_string(textwrap.dedent(""" + vtt = webvtt.from_string(textwrap.dedent(""" WEBVTT 00:00:00.500 --> 00:00:07.000 diff --git a/webvtt/__init__.py b/webvtt/__init__.py index 33fa037..301c17b 100644 --- a/webvtt/__init__.py +++ b/webvtt/__init__.py @@ -1,6 +1,8 @@ """Main webvtt package.""" __version__ = '0.5.0' +__author__ = 'Alejandro Mendez' +__author_email__ = 'amendez23@gmail.com' from .webvtt import WebVTT from . import segmenter @@ -13,4 +15,5 @@ from_buffer = WebVTT.from_buffer from_srt = WebVTT.from_srt from_sbv = WebVTT.from_sbv +from_string = WebVTT.from_string segment = segmenter.segment