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
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
|
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import os
import re
import pandoc
from tempfile import NamedTemporaryFile
from panfry.util import *
from panfry.page import TextFile, Page
class Document:
def __init__(self, path):
self.src_path = path
self.meta = self.get_meta(path)
self.pages = self.get_pages(path)
self.full_toc = True
self.css_file = 'css/style.css'
@property
def set_simple_toc(self):
self.full_toc = False
@property
def set_full_toc(self):
self.full_toc = True
def set_templater(self, templater):
self.templater = templater
def expand_int_links(self, source):
'''
Converts all internal links to full url links
so that links reference accross the split up html pages
Arguments:
source = original markdown source
returns: markdown source with expanded links
'''
re_link1 = re.compile(r'(\[(?P<s>[^\]^]+)\])\((?P<l>#.*)\)', re.S)
re_link2 = re.compile(r'(\[(?P<s>[^\]^]+)\][^(])', re.S)
source = re_link1.sub(self._get_cross_link, source)
source = re_link2.sub(self._get_cross_link, source)
return source
def _get_cross_link(self, m):
ref_txt = m.group('s')
for page in self.pages:
for tocitem in page.toc:
if tocitem.heading == ref_txt.replace('\n', ' '):
return '[%s](%s#%s)' % (ref_txt,
page.htmlfile,
tocitem.header_id,
)
return '[%s]' % ref_txt
@property
def title(self):
if self.header.firstline.startswith('%'):
title = self.header.firstline.split('%')[1].strip()
for line in self.header.lines[1:]:
if line.startswith('%'):
break
title = '%s %s' % (title, line.strip())
return title
else:
return pages[0].title
def get_pages(self, path):
pages = []
filelist = self.toc.lines
print filelist
for filename in filelist:
print("Reading in %s..." % filename)
if not filename: # blank line in toc
print("WARNING: %s contains blank lines" % self.toc.filename)
continue
source = read_file(os.path.join(path, filename))
if source:
pages.append(Page(filename, source))
else:
print("WARNING: Page: %s not found or is empty." % filename)
return pages
def get_meta(self, path):
metafiles = ['TOC', 'HEADER']
meta = {}
for filename in metafiles:
source = read_file(os.path.join(path, filename))
if source:
metafile = TextFile(filename, source)
setattr(self, filename.lower(), metafile)
else:
print("!E: %s not found or is empty. Aborting..." % filename)
exit(1)
return meta
def next_page(self, page):
try:
idx = self.pages.index(page)
except:
return ''
if idx >= len(self.pages) - 1:
return ''
return self.pages[idx+1]
def prev_page(self, page):
try:
idx = self.pages.index(page)
except:
return ''
if idx == 0:
return ''
return self.pages[idx-1]
@property
def toc_links(self):
'''
Returns a list of dictionaries. Each dictionary element contains
a page title and the html file name.
'''
links = []
for page in self.pages:
if self.full_toc:
toc = page.toc
else:
toc = [page.toc[0]]
for tocitem in toc:
link = '%s#%s' % (page.htmlfile, tocitem.header_id)
links.append(dict(link=unicode(link, "utf8"),
text=unicode(tocitem.heading, "utf8"),
level=tocitem.level,
))
return links
@property
def filename_base(self):
filename = self.title
filename = re.sub(r'\s+', ' ', filename)
filename = re.sub(r'[\n ]', '_', filename)
filename = re.sub(r'[:,]', '-', filename)
filename = re.sub(r'_+', '_', filename)
filename = re.sub(r'-_', '-', filename)
filename = re.sub(r'-+', '-', filename)
return filename
@property
def pdf_filename(self):
return self.filename_base + '.pdf'
@property
def epub_filename(self):
return self.filename_base + '.epub'
def publish_pdf(self, pub_path):
pdf_path = os.path.join(pub_path, self.pdf_filename)
src = self.header.source
for page in self.pages:
src += '\n%s' % page.source
doc = pandoc.Document()
doc.markdown = src
pandoc.set_cwd(os.path.abspath(self.src_path))
doc.add_argument('latex-engine=xelatex')
doc.to_file(pdf_path)
pandoc.set_cwd(None)
return self.pdf_filename
def publish_epub(self, pub_path):
epub_path = os.path.join(pub_path, self.epub_filename)
src = self.header.source
for page in self.pages:
src += '\n%s' % page.source
doc = pandoc.Document()
doc.markdown = src
pandoc.set_cwd(os.path.abspath(self.src_path))
doc.to_file(epub_path)
pandoc.set_cwd(None)
return self.epub_filename
def publish_css(self, pub_path):
src = os.path.join(self.src_path, 'css')
dst = os.path.join(pub_path, 'css')
if os.path.isdir(src):
copy(src, dst)
def publish_images(self, pub_path):
src_path = self.src_path
if os.path.exists(os.path.join(src_path, 'images/html')):
src = os.path.join(src_path, 'images/html')
else:
src = os.path.join(src_path, 'images')
dst = os.path.join(pub_path, 'images')
if os.path.exists(src):
copy(src, dst)
def publish_html(self, pub_path):
pandoc.set_cwd(None)
for page in self.pages:
print("generating %s..." % page.htmlfile)
template_file = NamedTemporaryFile(mode='w',
suffix='pf.template',
delete=False)
template = self.templater.page_template(self, page)
template_file.write(template)
template_file.close()
doc = pandoc.Document()
doc.add_argument('toc')
doc.add_argument('template=%s' % template_file.name)
doc.add_argument('css=%s' % self.css_file)
doc.markdown = '%s\n%s' % (self.header.source,
self.expand_int_links(page.markdown))
content = doc.html
write_file(os.path.join(pub_path, page.htmlfile),
unicode(content, 'utf-8'))
# If there is not explicit index.html, then link 'index.html'
# to the toplevel page.
if not 'index.md' in self.pages:
src = os.path.join(self.pages[0].htmlfile)
ref = os.path.join(pub_path, 'index.html')
os.symlink(src, ref)
###### Copy any images to publish directory
self.publish_css(pub_path)
self.publish_images(pub_path)
|
