1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
|
"""loads Markdown files, converts each one to HTML and parses the HTML into an ElementTree structure.
The collection of ElementTrees are further parsed to generate a table of contents structure, and are
manipulated to replace various markdown-generated HTML with specific Mako tags before being written
to Mako templates, which then re-access the table of contents structure at runtime.
Much thanks to Alexey Shamrin, who came up with the original idea and did all the heavy Markdown/Elementtree
lifting for this module."""
import sys, re, os
from toc import TOCElement
try:
import xml.etree.ElementTree as et
except:
try:
import elementtree.ElementTree as et
except:
raise "This module requires ElementTree to run (http://effbot.org/zone/element-index.htm)"
import markdown
def dump_tree(elem, stream):
if elem.tag.startswith('MAKO:'):
dump_mako_tag(elem, stream)
else:
if elem.tag != 'html':
if len(elem.attrib):
stream.write("<%s %s>" % (elem.tag, " ".join(["%s=%s" % (key, repr(val)) for key, val in elem.attrib.iteritems()])))
else:
stream.write("<%s>" % elem.tag)
if elem.text:
stream.write(elem.text)
for child in elem:
dump_tree(child, stream)
if child.tail:
stream.write(child.tail)
stream.write("</%s>" % elem.tag)
def dump_mako_tag(elem, stream):
tag = elem.tag[5:]
params = ','.join(['%s=%s' % i for i in elem.items()])
stream.write('<%%call expr="%s(%s)">' % (tag, params))
if elem.text:
stream.write(elem.text)
for n in elem:
dump_tree(n, stream)
if n.tail:
stream.write(n.tail)
stream.write("</%call>")
def create_toc(filename, tree, tocroot):
title = [None]
current = [tocroot]
level = [0]
def process(tree):
while True:
i = find_header_index(tree)
if i is None:
return
node = tree[i]
taglevel = int(node.tag[1])
start, end = i, end_of_header(tree, taglevel, i+1)
content = tree[start+1:end]
description = node.text.strip()
if title[0] is None:
title[0] = description
name = node.get('name')
if name is None:
name = description.split()[0].lower()
taglevel = node.tag[1]
if taglevel > level[0]:
current[0] = TOCElement(filename, name, description, current[0])
elif taglevel == level[0]:
current[0] = TOCElement(filename, name, description, current[0].parent)
else:
current[0] = TOCElement(filename, name, description, current[0].parent.parent)
level[0] = taglevel
tag = et.Element("MAKO:formatting.section", path=repr(current[0].path), paged='paged', extension='extension', toc='toc')
tag.text = (node.tail or "") + '\n'
tag.tail = '\n'
tag[:] = content
tree[start:end] = [tag]
process(tag)
process(tree)
return (title[0], tocroot.get_by_file(filename))
def index(parent, item):
for n, i in enumerate(parent):
if i is item:
return n
def find_header_index(tree):
for i, node in enumerate(tree):
if is_header(node):
return i
def is_header(node):
t = node.tag
return (isinstance(t, str) and len(t) == 2 and t[0] == 'h'
and t[1] in '123456789')
def end_of_header(tree, level, start):
for i, node in enumerate(tree[start:]):
if is_header(node) and int(node.tag[1]) <= level:
return start + i
return len(tree)
def process_rel_href(tree):
parent = get_parent_map(tree)
for a in tree.findall('.//a'):
m = re.match(r'(bold)?rel\:(.+)', a.get('href'))
if m:
(bold, path) = m.group(1,2)
text = a.text
if text == path:
tag = et.Element("MAKO:nav.toclink", path=repr(path), extension='extension', paged='paged', toc='toc')
else:
tag = et.Element("MAKO:nav.toclink", path=repr(path), description=repr(text), extension='extension', paged='paged', toc='toc')
a_parent = parent[a]
if bold:
bold = et.Element('strong')
bold.tail = a.tail
bold.append(tag)
a_parent[index(a_parent, a)] = bold
else:
tag.tail = a.tail
a_parent[index(a_parent, a)] = tag
def replace_pre_with_mako(tree):
parents = get_parent_map(tree)
for precode in tree.findall('.//pre/code'):
reg = re.compile(r'\{(python|mako|html|ini)(?: title="(.*?)"){0,1}\}(.*)', re.S)
m = reg.match(precode[0].text.lstrip())
if m:
code = m.group(1)
title = m.group(2)
precode[0].text = m.group(3)
else:
code = title = None
tag = et.Element("MAKO:formatting.code")
if code:
tag.attrib["syntaxtype"] = repr(code)
if title:
tag.attrib["title"] = repr(title)
tag.text = precode.text
[tag.append(x) for x in precode]
pre = parents[precode]
tag.tail = pre.tail
pre_parent = parents[pre]
pre_parent[reverse_parent(pre_parent, pre)] = tag
def safety_code(tree):
parents = get_parent_map(tree)
for code in tree.findall('.//code'):
tag = et.Element('%text')
if parents[code].tag != 'pre':
tag.attrib["filter"] = "h"
tag.text = code.text
code.append(tag)
code.text = ""
def reverse_parent(parent, item):
for n, i in enumerate(parent):
if i is item:
return n
def get_parent_map(tree):
return dict([(c, p) for p in tree.getiterator() for c in p])
def header(toc, title, filename):
return """# -*- coding: utf-8 -*-
<%%inherit file="content_layout.html"/>
<%%page args="toc, extension, paged"/>
<%%namespace name="formatting" file="formatting.html"/>
<%%namespace name="nav" file="nav.html"/>
<%%def name="title()">%s - %s</%%def>
<%%!
filename = '%s'
%%>
## This file is generated. Edit the .txt files instead of this one.
""" % (toc.root.doctitle, title, filename)
class utf8stream(object):
def __init__(self, stream):
self.stream = stream
def write(self, str):
self.stream.write(str.encode('utf8'))
def parse_markdown_files(toc, files):
for inname in files:
infile = 'content/%s.txt' % inname
if not os.access(infile, os.F_OK):
continue
html = markdown.markdown(file(infile).read())
tree = et.fromstring("<html>" + html + "</html>")
(title, toc_element) = create_toc(inname, tree, toc)
safety_code(tree)
replace_pre_with_mako(tree)
process_rel_href(tree)
outname = 'output/%s.html' % inname
print infile, '->', outname
outfile = utf8stream(file(outname, 'w'))
outfile.write(header(toc, title, inname))
dump_tree(tree, outfile)
|