sitescripts/web/converters.py - Issue 17817001: Simple CMS as Anwiki replacement

Side by Side Diff: sitescripts/web/converters.py

Issue 17817001: Simple CMS as Anwiki replacement (Closed)

Patch Set: Created Oct. 23, 2013, 1:52 p.m.

Left:
Right:

Use n/p to move between diff chunks; N/P to move between comments.

Jump to:

View unified diff | Download patch

OLD	NEW
(Empty)
	1 # coding: utf-8

	2

	3 # This file is part of the Adblock Plus web scripts,

	4 # Copyright (C) 2006-2013 Eyeo GmbH

	5 #

	6 # Adblock Plus is free software: you can redistribute it and/or modify

	7 # it under the terms of the GNU General Public License version 3 as

	8 # published by the Free Software Foundation.

	9 #

	10 # Adblock Plus is distributed in the hope that it will be useful,

	11 # but WITHOUT ANY WARRANTY; without even the implied warranty of

	12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the

	13 # GNU General Public License for more details.

	14 #

	15 # You should have received a copy of the GNU General Public License

	16 # along with Adblock Plus. If not, see <http://www.gnu.org/licenses/>.

	17

	18 import re, jinja2, markdown

	19 from sitescripts.utils import cached, setupStderr, get_custom_template_environme nt

	20

	21 # Monkey-patch Markdown's isBlockLevel function to ensure that no paragraphs are

	22 # inserted into the <head> tag

	23 orig_isBlockLevel = markdown.util.isBlockLevel

	24 def isBlockLevel(tag):

	25 if tag == "head":

	26 return True

	27 else:

	28 return orig_isBlockLevel(tag)

	29 markdown.util.isBlockLevel = isBlockLevel

	30

	31 def split_head(text):

	32 head = []

	33 def add_to_head(match):

	34 head.append(match.group(1))

	35 return ""

	36 body = re.sub(r"<head>(.*?)</head>",

	37 add_to_head, text, flags=re.S)

	38 return "".join(head), body

	39

	40 class MarkdownConverter:

	41 class Localizer(markdown.preprocessors.Preprocessor):

	42 def __init__(self, params):

	43 self._params = params

	44

	45 self._escaped = set(markdown.Markdown.ESCAPED_CHARS)

	46 self._escaped.add("<");

	47 self._escaped.add(">");

	48 self._escaped.add("&");

	49 self._escaped.add("\"");

	50 self._escaped.add("'");

	51

	52 def run(self, lines):

	53 new_lines = []

	54 for line in lines:

	55 # Replace localized strings

	56 new_lines.append(re.sub(r"\$([\w\-]+)($[^()$]+$)?\$",

	57 lambda match: self.lookup_string(match.group(1), match.group(2)),

	58 line))

	59 return new_lines

	60

	61 def lookup_string(self, name, links):

	62 def escape(char):

	63 if char in self._escaped:

	64 return "&#" + str(ord(char)) + ";"

	65 else:

	66 return char

	67

	68 try:

	69 result = self._params["localedata"][name].strip()

	70 except KeyError:

	71 raise Exception("Lookup failed for string %s used on page %s" % (name, s elf._params["page"]))

	72

	73 result = re.sub(r".", lambda match: escape(match.group(0)), result, flags= re.S)

	74 if links:

	75 links = map(unicode.strip, links.strip("()").split(","))

	76 while len(links):

	77 result = re.sub(r"<a>(.*?)</a>", r'<a href="%s">\1</a> ' % links.pop(0), result, 1, flags=re.S)

	78 return result

	79

	80 class Linkifier(markdown.postprocessors.Postprocessor):

	81 def __init__(self, params):

	82 self._params = params

	83

	84 def process_link(self, match):

	85 pre, attr, url, post = match.groups()

	86 url = jinja2.Markup(url).unescape()

	87

	88 locale, new_url = self._params["source"].resolve_link(url, self._params["l ocale"])

	89 if new_url != None:

	90 url = new_url

	91 if attr == "href":

	92 post += ' hreflang="%s"' % jinja2.Markup.escape(locale)

	93

	94 return "".join((pre, jinja2.Markup.escape(url), post))

	95

	96 def run(self, text):

	97 text = re.sub(r"(<a [^<>]*\b(href)=\")([^<>\"]+)(\")", self.process_link, text)

	98 text = re.sub(r"(<img [^<>]*\b(src)=\")([^<>\"]+)(\")", self.process_link, text)

	99 return text

	100

	101 def __init__(self, params, key="pagedata"):

	102 self._params = params

	103 self._splithead = key == "pagedata"

	104

	105 self._md = markdown.Markdown(output="html5", extensions=["attr_list"])

	106 self._md.preprocessors.add("localizer", self.Localizer(params), "_begin")

	107 self._md.postprocessors.add("linkifier", self.Linkifier(params), "_end")

	108

	109 params["pagedata"] = params["pagedata"].decode("utf-8")

	110

	111 # Read in any parameters specified at the beginning of the file

	112 lines = params["pagedata"].splitlines(True)

	113 while len(lines) and re.search(r"^\s[\w\-]+\s=", lines[0]):

	114 key, value = lines.pop(0).split("=", 1)

	115 params[key.strip()] = value.strip()

	116 params["pagedata"] = "".join(lines)

	117

	118 def __call__(self):

	119 def beautify_entities(match):

	120 escape = {

	121 "<": "<",

	122 ">": ">",

	123 "&": "&",

	124 "\"": """,

	125 "'": "'",

	126 }

	127 char = chr(int(match.group(1)))

	128 return escape.get(char, char)

	129

	130 result = self._md.convert(self._params["pagedata"])

	131 result = re.sub(r"&#(\d+);", beautify_entities, result).encode("utf-8")

	132

	133 if self._splithead:

	134 return split_head(result)

	135 else:

	136 return result

	137

	138 class TemplateConverter:

	139 def __init__(self, params, key="pagedata"):

	140 self._params = params

	141 self._splithead = key == "pagedata"

	142 filters = {

	143 "translate": self.translate,

	144 "linkify": self.linkify,

	145 "toclist": self.toclist,

	146 }

	147 env = get_custom_template_environment(filters)

	148 self._template = env.from_string(params[key].decode("utf-8"))

	149

	150 def __call__(self):

	151 result = self._template.render(self._params).encode("utf-8")

	152 if self._splithead:

	153 return split_head(result)

	154 else:

	155 return result

	156

	157 def translate(self, name, page=None):

	158 if page == None:

	159 localedata = self._params["localedata"]

	160 else:

	161 localedata = self._params["source"].read_locale(self._params["locale"], pa ge)

	162

	163 try:

	164 return localedata[name]

	165 except KeyError:

	166 raise Exception("Lookup failed for string %s used on page %s" % (name, sel f._params["page"]))

	167

	168 def linkify(self, page, locale=None):

	169 if locale == None:

	170 locale = self._params["locale"]

	171

	172 locale, url = self._params["source"].resolve_link(page, locale)

	173 return jinja2.Markup('<a href="%s" hreflang="%s">' % (

	174 jinja2.Markup.escape(url),

	175 jinja2.Markup.escape(locale)

	176 ))

	177

	178 def toclist(self, content):

	179 flat = []

	180 for match in re.finditer(r'<h(\d) [^<>]\bid="([^<>"]+)"[^<>]>(.*?)</h\1>', content, re.S):

	181 flat.append({

	182 "level": int(match.group(1)),

	183 "anchor": jinja2.Markup(match.group(2)).unescape(),

	184 "title": jinja2.Markup(match.group(3)).unescape(),

	185 "subitems": [],

	186 })

	187

	188 structured = []

	189 stack = [{"level": 0, "subitems": structured}]

	190 for item in flat:

	191 while stack[-1]["level"] >= item["level"]:

	192 stack.pop()

	193 stack[-1]["subitems"].append(item)

	194 stack.append(item)

	195 return structured

	196

	197 converters = {

	198 "md": MarkdownConverter,

	199 "tmpl": TemplateConverter,

	200 }

OLD	NEW

« no previous file with comments | « sitescripts/web/bin/test_server.py ('k') | sitescripts/web/sources.py » ('j') | no next file with comments »