Hello community, here is the log from the commit of package python3-html2text for openSUSE:Factory checked in at 2015-04-15 16:24:55 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Comparing /work/SRC/openSUSE:Factory/python3-html2text (Old) and /work/SRC/openSUSE:Factory/.python3-html2text.new (New) ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "python3-html2text" Changes: -------- --- /work/SRC/openSUSE:Factory/python3-html2text/python3-html2text.changes 2015-02-20 12:01:56.000000000 +0100 +++ /work/SRC/openSUSE:Factory/.python3-html2text.new/python3-html2text.changes 2015-04-15 16:24:59.000000000 +0200 @@ -1,0 +2,14 @@ +Tue Apr 14 22:48:37 UTC 2015 - [email protected] + +- update to version 2015.4.14: + * Feature #59: Write image tags with height and width attrs as raw html to retain dimensions + +------------------------------------------------------------------- +Tue Apr 14 04:19:18 UTC 2015 - [email protected] + +- update to version 2015.4.13: + * Feature #56: Treat '-' file parameter as stdin. + * Feature #57: Retain escaping of html except within code or pre + tags. + +------------------------------------------------------------------- Old: ---- html2text-2015.2.18.tar.gz New: ---- html2text-2015.4.14.tar.gz ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Other differences: ------------------ ++++++ python3-html2text.spec ++++++ --- /var/tmp/diff_new_pack.cjBpp5/_old 2015-04-15 16:25:00.000000000 +0200 +++ /var/tmp/diff_new_pack.cjBpp5/_new 2015-04-15 16:25:00.000000000 +0200 @@ -17,7 +17,7 @@ Name: python3-html2text -Version: 2015.2.18 +Version: 2015.4.14 Release: 0 Url: https://github.com/Alir3z4/html2text/ Summary: Turn HTML into equivalent Markdown-structured text ++++++ html2text-2015.2.18.tar.gz -> html2text-2015.4.14.tar.gz ++++++ diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html2text-2015.2.18/AUTHORS.rst new/html2text-2015.4.14/AUTHORS.rst --- old/html2text-2015.2.18/AUTHORS.rst 2015-02-18 14:16:15.000000000 +0100 +++ new/html2text-2015.4.14/AUTHORS.rst 2015-04-13 17:48:22.000000000 +0200 @@ -12,6 +12,9 @@ * Jocelyn Delalande <[email protected]> * Matt Dorn <[email protected]> * Miguel Tavares <[email protected]> +* Scott Blackburn <[email protected]> +* Peter Wu <[email protected]> + Maintainer: diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html2text-2015.2.18/ChangeLog.rst new/html2text-2015.4.14/ChangeLog.rst --- old/html2text-2015.2.18/ChangeLog.rst 2015-02-18 14:20:44.000000000 +0100 +++ new/html2text-2015.4.14/ChangeLog.rst 2015-04-14 19:05:05.000000000 +0200 @@ -1,3 +1,20 @@ +2015.4.14 +========= +---- + + +* Feature #59: Write image tags with height and width attrs as raw html to retain dimensions + + +2015.4.13 +========= +---- + + +* Feature #56: Treat '-' file parameter as stdin. +* Feature #57: Retain escaping of html except within code or pre tags. + + 2015.2.18 ========== ---- diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html2text-2015.2.18/PKG-INFO new/html2text-2015.4.14/PKG-INFO --- old/html2text-2015.2.18/PKG-INFO 2015-02-18 14:23:58.000000000 +0100 +++ new/html2text-2015.4.14/PKG-INFO 2015-04-14 19:09:30.000000000 +0200 @@ -1,6 +1,6 @@ Metadata-Version: 1.1 Name: html2text -Version: 2015.2.18 +Version: 2015.4.14 Summary: Turn HTML into equivalent Markdown-structured text. Home-page: https://github.com/Alir3z4/html2text/ Author: Alireza Savand diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html2text-2015.2.18/README.md new/html2text-2015.4.14/README.md --- old/html2text-2015.2.18/README.md 2015-02-18 14:16:15.000000000 +0100 +++ new/html2text-2015.4.14/README.md 2015-04-14 19:05:05.000000000 +0200 @@ -16,14 +16,15 @@ Usage: `html2text [(filename|url) [encoding]]` -| Option | Description +| Option | Description |--------------------------------------------------------|--------------------------------------------------- -| `--version` | Show program's version number and exit -| `-h`, `--help` | Show this help message and exit +| `--version` | Show program's version number and exit +| `-h`, `--help` | Show this help message and exit | `--ignore-links` | Don't include any formatting for links |`--protect-links` | Protect links from line breaks surrounding them "+" with angle brackets |`--ignore-images` | Don't include any formatting for images |`--images-to-alt` | Discard image data, only keep alt text +|`--images-with-size` | Write image tags with height and width attrs as raw html to retain dimensions |`-g`, `--google-doc` | Convert an html-exported Google Document |`-d`, `--dash-unordered-list` | Use a dash rather than a star for unordered list items |`-b` `BODY_WIDTH`, `--body-width`=`BODY_WIDTH` | Number of characters per output line, `0` for no wrap @@ -48,7 +49,7 @@ Or with some configuration options: ``` >>> import html2text ->>> +>>> >>> h = html2text.HTML2Text() >>> # Ignore converting links from HTML >>> h.ignore_links = True diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html2text-2015.2.18/html2text/__init__.py new/html2text-2015.4.14/html2text/__init__.py --- old/html2text-2015.2.18/html2text/__init__.py 2015-02-18 14:16:15.000000000 +0100 +++ new/html2text-2015.4.14/html2text/__init__.py 2015-04-14 19:09:03.000000000 +0200 @@ -3,6 +3,7 @@ """html2text: Turn HTML into equivalent Markdown-structured text.""" from __future__ import division import re +import cgi try: from textwrap import wrap @@ -28,7 +29,7 @@ skipwrap ) -__version__ = "2014.12.29" +__version__ = "2015.4.14" # TODO: @@ -60,6 +61,7 @@ self.ignore_links = config.IGNORE_ANCHORS self.ignore_images = config.IGNORE_IMAGES self.images_to_alt = config.IMAGES_TO_ALT + self.images_with_size = config.IMAGES_WITH_SIZE self.ignore_emphasis = config.IGNORE_EMPHASIS self.bypass_tables = config.BYPASS_TABLES self.google_doc = False @@ -160,10 +162,16 @@ return outtext def handle_charref(self, c): - self.o(self.charref(c), 1) + charref = self.charref(c) + if not self.code and not self.pre: + charref = cgi.escape(charref) + self.o(charref, 1) def handle_entityref(self, c): - self.o(self.entityref(c), 1) + entityref = self.entityref(c) + if not self.code and not self.pre and entityref != ' _place_holder;': + entityref = cgi.escape(entityref) + self.o(entityref, 1) def handle_starttag(self, tag, attrs): self.handle_tag(tag, attrs, 1) @@ -351,6 +359,7 @@ if tag in ["code", "tt"] and not self.pre: self.o('`') # TODO: `` `this` `` + self.code = not self.code if tag == "abbr": if start: self.abbr_title = None @@ -405,6 +414,20 @@ attrs['href'] = attrs['src'] alt = attrs.get('alt') or '' + # If we have images_with_size, write raw html including width, + # height, and alt attributes + if self.images_with_size and \ + ("width" in attrs or "height" in attrs): + self.o("<img src='" + attrs["src"] + "' ") + if "width" in attrs: + self.o("width='" + attrs["width"] + "' ") + if "height" in attrs: + self.o("height='" + attrs["height"] + "' ") + if alt: + self.o("alt='" + alt + "' ") + self.o("/>") + return + # If we have a link to create, output the start if not self.maybe_automatic_link is None: href = self.maybe_automatic_link @@ -416,7 +439,7 @@ else: self.o("[") self.maybe_automatic_link = None - self.empty_link = False + self.empty_link = False # If we have images_to_alt, we discard the image itself, # considering only the alt text. diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html2text-2015.2.18/html2text/cli.py new/html2text-2015.4.14/html2text/cli.py --- old/html2text-2015.2.18/html2text/cli.py 2015-02-18 14:16:15.000000000 +0100 +++ new/html2text-2015.4.14/html2text/cli.py 2015-04-14 19:05:05.000000000 +0200 @@ -45,6 +45,14 @@ help="Discard image data, only keep alt text" ) p.add_option( + "--images-with-size", + dest="images_with_size", + action="store_true", + default=config.IMAGES_WITH_SIZE, + help="Write image tags with height and width attrs as raw html to " + "retain dimensions" + ) + p.add_option( "-g", "--google-doc", action="store_true", dest="google_doc", @@ -118,7 +126,7 @@ # process input encoding = "utf-8" - if len(args) > 0: + if len(args) > 0 and args[0] != '-': file_ = args[0] if len(args) == 2: encoding = args[1] @@ -166,6 +174,7 @@ h.protect_links = options.protect_links h.ignore_images = options.ignore_images h.images_to_alt = options.images_to_alt + h.images_with_size = options.images_with_size h.google_doc = options.google_doc h.hide_strikethrough = options.hide_strikethrough h.escape_snob = options.escape_snob diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html2text-2015.2.18/html2text/config.py new/html2text-2015.4.14/html2text/config.py --- old/html2text-2015.2.18/html2text/config.py 2015-02-18 14:16:15.000000000 +0100 +++ new/html2text-2015.4.14/html2text/config.py 2015-04-14 19:05:05.000000000 +0200 @@ -30,6 +30,7 @@ IGNORE_ANCHORS = False IGNORE_IMAGES = False IMAGES_TO_ALT = False +IMAGES_WITH_SIZE = False IGNORE_EMPHASIS = False # For checking space-only lines on line 771 diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html2text-2015.2.18/html2text.egg-info/PKG-INFO new/html2text-2015.4.14/html2text.egg-info/PKG-INFO --- old/html2text-2015.2.18/html2text.egg-info/PKG-INFO 2015-02-18 14:23:58.000000000 +0100 +++ new/html2text-2015.4.14/html2text.egg-info/PKG-INFO 2015-04-14 19:09:30.000000000 +0200 @@ -1,6 +1,6 @@ Metadata-Version: 1.1 Name: html2text -Version: 2015.2.18 +Version: 2015.4.14 Summary: Turn HTML into equivalent Markdown-structured text. Home-page: https://github.com/Alir3z4/html2text/ Author: Alireza Savand diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html2text-2015.2.18/html2text.egg-info/SOURCES.txt new/html2text-2015.4.14/html2text.egg-info/SOURCES.txt --- old/html2text-2015.2.18/html2text.egg-info/SOURCES.txt 2015-02-18 14:23:58.000000000 +0100 +++ new/html2text-2015.4.14/html2text.egg-info/SOURCES.txt 2015-04-14 19:09:30.000000000 +0200 @@ -35,8 +35,12 @@ test/emdash-para.md test/empty-link.html test/empty-link.md +test/html-escaping.html +test/html-escaping.md test/images_to_alt.html test/images_to_alt.md +test/images_with_size.html +test/images_with_size.md test/img-tag-with-link.html test/img-tag-with-link.md test/invalid_start.html diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html2text-2015.2.18/setup.py new/html2text-2015.4.14/setup.py --- old/html2text-2015.2.18/setup.py 2015-02-18 14:20:44.000000000 +0100 +++ new/html2text-2015.4.14/setup.py 2015-04-14 19:08:44.000000000 +0200 @@ -34,7 +34,7 @@ setup( name="html2text", - version="2015.2.18", + version="2015.4.14", description="Turn HTML into equivalent Markdown-structured text.", author="Aaron Swartz", author_email="[email protected]", diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html2text-2015.2.18/test/html-escaping.html new/html2text-2015.4.14/test/html-escaping.html --- old/html2text-2015.2.18/test/html-escaping.html 1970-01-01 01:00:00.000000000 +0100 +++ new/html2text-2015.4.14/test/html-escaping.html 2015-04-13 17:28:02.000000000 +0200 @@ -0,0 +1,3 @@ +<p>Escaped HTML like <div> or & should remain escaped on output</p> +<pre>...unless that escaped HTML is in a <pre> tag</pre> +<code>...or a <code> tag</code> \ No newline at end of file diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html2text-2015.2.18/test/html-escaping.md new/html2text-2015.4.14/test/html-escaping.md --- old/html2text-2015.2.18/test/html-escaping.md 1970-01-01 01:00:00.000000000 +0100 +++ new/html2text-2015.4.14/test/html-escaping.md 2015-04-13 17:28:02.000000000 +0200 @@ -0,0 +1,8 @@ +Escaped HTML like <div> or & should remain escaped on output + + + + ...unless that escaped HTML is in a <pre> tag + +`...or a <code> tag` + diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html2text-2015.2.18/test/images_with_size.html new/html2text-2015.4.14/test/images_with_size.html --- old/html2text-2015.2.18/test/images_with_size.html 1970-01-01 01:00:00.000000000 +0100 +++ new/html2text-2015.4.14/test/images_with_size.html 2015-04-14 19:05:05.000000000 +0200 @@ -0,0 +1,7 @@ +<img src='image_without_dimensions.jpg' alt='An image without dimensions' style='ignored-style' /> + +<img src='image_with_width.jpg' alt='An image with a width attr' width='300' data-ignored='ignored data' /> + +<img src='image_with_width.jpg' alt='An image with a height attr' height='300' data-ignored='ignored data' /> + +<img src='image_with_width_and_height.jpg' alt='An image with width and height' width='300' height='300' id='ignored-id' /> \ No newline at end of file diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html2text-2015.2.18/test/images_with_size.md new/html2text-2015.4.14/test/images_with_size.md --- old/html2text-2015.2.18/test/images_with_size.md 1970-01-01 01:00:00.000000000 +0100 +++ new/html2text-2015.4.14/test/images_with_size.md 2015-04-14 19:05:05.000000000 +0200 @@ -0,0 +1,6 @@ + <img +src='image_with_width.jpg' width='300' alt='An image with a width attr' /> +<img src='image_with_width.jpg' height='300' alt='An image with a height attr' +/> <img src='image_with_width_and_height.jpg' width='300' height='300' alt='An +image with width and height' /> + diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html2text-2015.2.18/test/test_html2text.py new/html2text-2015.4.14/test/test_html2text.py --- old/html2text-2015.2.18/test/test_html2text.py 2015-02-18 14:16:15.000000000 +0100 +++ new/html2text-2015.4.14/test/test_html2text.py 2015-04-14 19:05:05.000000000 +0200 @@ -135,6 +135,10 @@ module_args['images_to_alt'] = True cmdline_args.append('--images-to-alt') + if base_fn.startswith('images_with_size'): + module_args['images_with_size'] = True + cmdline_args.append('--images-with-size') + if base_fn.startswith('single_line_break'): module_args['body_width'] = 0 cmdline_args.append('--body-width=0')
