Unified Diff: sitescripts/web/converters.py
Issue 17817001:
Simple CMS as Anwiki replacement (Closed)
Patch Set:
Created Oct. 23, 2013, 1:52 p.m.
Use n/p to move between diff chunks;
N/P to move between comments.
« no previous file with comments
|
« sitescripts/web/bin/test_server.py ('k')
|
sitescripts/web/sources.py » ('j')
|
no next file with comments »
Expand Comments ('e') | Collapse Comments ('c') | Hide Comments ('s')
Expand Comments ('e') | Collapse Comments ('c') | Hide Comments ('s')
| Index: sitescripts/web/converters.py |
| =================================================================== |
| new file mode 100644 |
| --- /dev/null |
| +++ b/sitescripts/web/converters.py |
| @@ -0,0 +1,200 @@ |
| +# coding: utf-8 |
| + |
| +# This file is part of the Adblock Plus web scripts, |
| +# Copyright (C) 2006-2013 Eyeo GmbH |
| +# |
| +# Adblock Plus is free software: you can redistribute it and/or modify |
| +# it under the terms of the GNU General Public License version 3 as |
| +# published by the Free Software Foundation. |
| +# |
| +# Adblock Plus is distributed in the hope that it will be useful, |
| +# but WITHOUT ANY WARRANTY; without even the implied warranty of |
| +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| +# GNU General Public License for more details. |
| +# |
| +# You should have received a copy of the GNU General Public License |
| +# along with Adblock Plus. If not, see <http://www.gnu.org/licenses/>. |
| + |
| +import re, jinja2, markdown |
| +from sitescripts.utils import cached, setupStderr, get_custom_template_environment |
| + |
| +# Monkey-patch Markdown's isBlockLevel function to ensure that no paragraphs are |
| +# inserted into the <head> tag |
| +orig_isBlockLevel = markdown.util.isBlockLevel |
| +def isBlockLevel(tag): |
| + if tag == "head": |
| + return True |
| + else: |
| + return orig_isBlockLevel(tag) |
| +markdown.util.isBlockLevel = isBlockLevel |
| + |
| +def split_head(text): |
| + head = [] |
| + def add_to_head(match): |
| + head.append(match.group(1)) |
| + return "" |
| + body = re.sub(r"<head>(.*?)</head>", |
| + add_to_head, text, flags=re.S) |
| + return "".join(head), body |
| + |
| +class MarkdownConverter: |
| + class Localizer(markdown.preprocessors.Preprocessor): |
| + def __init__(self, params): |
| + self._params = params |
| + |
| + self._escaped = set(markdown.Markdown.ESCAPED_CHARS) |
| + self._escaped.add("<"); |
| + self._escaped.add(">"); |
| + self._escaped.add("&"); |
| + self._escaped.add("\""); |
| + self._escaped.add("'"); |
| + |
| + def run(self, lines): |
| + new_lines = [] |
| + for line in lines: |
| + # Replace localized strings |
| + new_lines.append(re.sub(r"\$([\w\-]+)(\([^()$]+\))?\$", |
| + lambda match: self.lookup_string(match.group(1), match.group(2)), |
| + line)) |
| + return new_lines |
| + |
| + def lookup_string(self, name, links): |
| + def escape(char): |
| + if char in self._escaped: |
| + return "&#" + str(ord(char)) + ";" |
| + else: |
| + return char |
| + |
| + try: |
| + result = self._params["localedata"][name].strip() |
| + except KeyError: |
| + raise Exception("Lookup failed for string %s used on page %s" % (name, self._params["page"])) |
| + |
| + result = re.sub(r".", lambda match: escape(match.group(0)), result, flags=re.S) |
| + if links: |
| + links = map(unicode.strip, links.strip("()").split(",")) |
| + while len(links): |
| + result = re.sub(r"<a>(.*?)</a>", r'<a href="%s">\1</a>' % links.pop(0), result, 1, flags=re.S) |
| + return result |
| + |
| + class Linkifier(markdown.postprocessors.Postprocessor): |
| + def __init__(self, params): |
| + self._params = params |
| + |
| + def process_link(self, match): |
| + pre, attr, url, post = match.groups() |
| + url = jinja2.Markup(url).unescape() |
| + |
| + locale, new_url = self._params["source"].resolve_link(url, self._params["locale"]) |
| + if new_url != None: |
| + url = new_url |
| + if attr == "href": |
| + post += ' hreflang="%s"' % jinja2.Markup.escape(locale) |
| + |
| + return "".join((pre, jinja2.Markup.escape(url), post)) |
| + |
| + def run(self, text): |
| + text = re.sub(r"(<a [^<>]*\b(href)=\")([^<>\"]+)(\")", self.process_link, text) |
| + text = re.sub(r"(<img [^<>]*\b(src)=\")([^<>\"]+)(\")", self.process_link, text) |
| + return text |
| + |
| + def __init__(self, params, key="pagedata"): |
| + self._params = params |
| + self._splithead = key == "pagedata" |
| + |
| + self._md = markdown.Markdown(output="html5", extensions=["attr_list"]) |
| + self._md.preprocessors.add("localizer", self.Localizer(params), "_begin") |
| + self._md.postprocessors.add("linkifier", self.Linkifier(params), "_end") |
| + |
| + params["pagedata"] = params["pagedata"].decode("utf-8") |
| + |
| + # Read in any parameters specified at the beginning of the file |
| + lines = params["pagedata"].splitlines(True) |
| + while len(lines) and re.search(r"^\s*[\w\-]+\s*=", lines[0]): |
| + key, value = lines.pop(0).split("=", 1) |
| + params[key.strip()] = value.strip() |
| + params["pagedata"] = "".join(lines) |
| + |
| + def __call__(self): |
| + def beautify_entities(match): |
| + escape = { |
| + "<": "<", |
| + ">": ">", |
| + "&": "&", |
| + "\"": """, |
| + "'": "'", |
| + } |
| + char = chr(int(match.group(1))) |
| + return escape.get(char, char) |
| + |
| + result = self._md.convert(self._params["pagedata"]) |
| + result = re.sub(r"&#(\d+);", beautify_entities, result).encode("utf-8") |
| + |
| + if self._splithead: |
| + return split_head(result) |
| + else: |
| + return result |
| + |
| +class TemplateConverter: |
| + def __init__(self, params, key="pagedata"): |
| + self._params = params |
| + self._splithead = key == "pagedata" |
| + filters = { |
| + "translate": self.translate, |
| + "linkify": self.linkify, |
| + "toclist": self.toclist, |
| + } |
| + env = get_custom_template_environment(filters) |
| + self._template = env.from_string(params[key].decode("utf-8")) |
| + |
| + def __call__(self): |
| + result = self._template.render(self._params).encode("utf-8") |
| + if self._splithead: |
| + return split_head(result) |
| + else: |
| + return result |
| + |
| + def translate(self, name, page=None): |
| + if page == None: |
| + localedata = self._params["localedata"] |
| + else: |
| + localedata = self._params["source"].read_locale(self._params["locale"], page) |
| + |
| + try: |
| + return localedata[name] |
| + except KeyError: |
| + raise Exception("Lookup failed for string %s used on page %s" % (name, self._params["page"])) |
| + |
| + def linkify(self, page, locale=None): |
| + if locale == None: |
| + locale = self._params["locale"] |
| + |
| + locale, url = self._params["source"].resolve_link(page, locale) |
| + return jinja2.Markup('<a href="%s" hreflang="%s">' % ( |
| + jinja2.Markup.escape(url), |
| + jinja2.Markup.escape(locale) |
| + )) |
| + |
| + def toclist(self, content): |
| + flat = [] |
| + for match in re.finditer(r'<h(\d) [^<>]*\bid="([^<>"]+)"[^<>]*>(.*?)</h\1>', content, re.S): |
| + flat.append({ |
| + "level": int(match.group(1)), |
| + "anchor": jinja2.Markup(match.group(2)).unescape(), |
| + "title": jinja2.Markup(match.group(3)).unescape(), |
| + "subitems": [], |
| + }) |
| + |
| + structured = [] |
| + stack = [{"level": 0, "subitems": structured}] |
| + for item in flat: |
| + while stack[-1]["level"] >= item["level"]: |
| + stack.pop() |
| + stack[-1]["subitems"].append(item) |
| + stack.append(item) |
| + return structured |
| + |
| +converters = { |
| + "md": MarkdownConverter, |
| + "tmpl": TemplateConverter, |
| +} |
« no previous file with comments
|
« sitescripts/web/bin/test_server.py ('k')
|
sitescripts/web/sources.py » ('j')
|
no next file with comments »
