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
|
#!/usr/bin/env python
###############################################################################
# Takes a chapter as input and adds internal links and numbering to all
# of the H1, H2, H3, H4 and H5 sections.
#
# Every heading HTML tag (H1, H2 etc) is given an autogenerated name to link
# to. However, if the name is not an autogenerated name from a previous run,
# it will be kept. If it is autogenerated, it might change on subsequent runs
# of this program. Thus if you want to create links to one of the headings,
# then change the heading link name to something that does not look like an
# autogenerated link name.
###############################################################################
import sys
import re
import string
###############################################################################
# Functions
###############################################################################
# Regexs for <a name="..."></a>
alink = re.compile(r"<a *name *= *\"(.*)\">.*</a>", re.IGNORECASE)
heading = re.compile(r"(_nn\d)", re.IGNORECASE)
def getheadingname(m):
autogeneratedheading = True;
if m.group(1) != None:
amatch = alink.match(m.group(1))
if amatch:
# A non-autogenerated heading - keep it
headingname = amatch.group(1)
autogeneratedheading = heading.match(headingname)
if autogeneratedheading:
# The heading name was either non-existent or autogenerated,
# We can create a new heading / change the existing heading
headingname = "%s_nn%d" % (filenamebase, nameindex)
return headingname
# Return heading - 1.1. Introduction in the examples below:
# old style example: <H2><a name="Preface_nn2"></a>1.1 Introduction</H2>
# new style example: <H2><a name="Preface_nn2">1.1 Introduction</a></H2>
def getheadingtext(m, s):
prevheadingtext_newstyle = m.group(2)
prevheadingtext_oldstyle = m.group(3)
if len(prevheadingtext_oldstyle) == 0 and len(prevheadingtext_newstyle) == 0:
raise RuntimeError("No heading text in line:\n%s" % s)
if len(prevheadingtext_oldstyle) > 0 and len(prevheadingtext_newstyle) > 0:
raise RuntimeError("Two heading texts, only one should be specified in line:\n%s" % s)
prevheadingtext = prevheadingtext_oldstyle if len(prevheadingtext_oldstyle) > 0 else prevheadingtext_newstyle
return prevheadingtext
###############################################################################
# Main program
###############################################################################
if len(sys.argv) != 3:
print "usage: makechap.py filename num"
sys.exit(1)
filename = sys.argv[1]
filenamebase = string.split(filename,".")[0]
num = int(sys.argv[2])
section = 0
subsection = 0
subsubsection = 0
nameindex = 0
name = ""
# Regexs for <h1>,... <h5> sections
h1 = re.compile(r".*?<H1>(<a.*?>\s*[\d\s]*(.*?)</a>)*[\d\s]*(.*?)</H1>", re.IGNORECASE)
h2 = re.compile(r".*?<H2>(<a.*?>\s*[\d\.\s]*(.*?)</a>)*[\d\.\s]*(.*?)</H2>", re.IGNORECASE)
h3 = re.compile(r".*?<H3>(<a.*?>\s*[\d\.\s]*(.*?)</a>)*[\d\.\s]*(.*?)</H3>", re.IGNORECASE)
h4 = re.compile(r".*?<H4>(<a.*?>\s*[\d\.\s]*(.*?)</a>)*[\d\.\s]*(.*?)</H4>", re.IGNORECASE)
h5 = re.compile(r".*?<H5>(<a.*?>\s*[\d\.\s]*(.*?)</a>)*[\d\.\s]*(.*?)</H5>", re.IGNORECASE)
data = open(filename).read() # Read data
open(filename+".bak","w").write(data) # Make backup
lines = data.splitlines()
result = [ ] # This is the result of postprocessing the file
index = "<!-- INDEX -->\n<div class=\"sectiontoc\">\n" # index contains the index for adding at the top of the file. Also printed to stdout.
skip = 0
skipspace = 0
for s in lines:
if s == "<!-- INDEX -->":
if not skip:
skip = 1
else:
skip = 0
continue;
if skip:
continue
if not s and skipspace:
continue
if skipspace:
result.append("")
result.append("")
skipspace = 0
m = h1.match(s)
if m:
prevheadingtext = getheadingtext(m, s)
nameindex += 1
headingname = getheadingname(m)
result.append("""<H1><a name="%s">%d %s</a></H1>""" % (headingname,num,prevheadingtext))
result.append("@INDEX@")
section = 0
subsection = 0
subsubsection = 0
subsubsubsection = 0
name = prevheadingtext
skipspace = 1
continue
m = h2.match(s)
if m:
prevheadingtext = getheadingtext(m, s)
nameindex += 1
section += 1
headingname = getheadingname(m)
result.append("""<H2><a name="%s">%d.%d %s</a></H2>""" % (headingname,num,section, prevheadingtext))
if subsubsubsection:
index += "</ul>\n"
if subsubsection:
index += "</ul>\n"
if subsection:
index += "</ul>\n"
if section == 1:
index += "<ul>\n"
index += """<li><a href="#%s">%s</a>\n""" % (headingname,prevheadingtext)
subsection = 0
subsubsection = 0
subsubsubsection = 0
skipspace = 1
continue
m = h3.match(s)
if m:
prevheadingtext = getheadingtext(m, s)
nameindex += 1
subsection += 1
headingname = getheadingname(m)
result.append("""<H3><a name="%s">%d.%d.%d %s</a></H3>""" % (headingname,num,section, subsection, prevheadingtext))
if subsubsubsection:
index += "</ul>\n"
if subsubsection:
index += "</ul>\n"
if subsection == 1:
index += "<ul>\n"
index += """<li><a href="#%s">%s</a>\n""" % (headingname,prevheadingtext)
subsubsection = 0
skipspace = 1
continue
m = h4.match(s)
if m:
prevheadingtext = getheadingtext(m, s)
nameindex += 1
subsubsection += 1
headingname = getheadingname(m)
result.append("""<H4><a name="%s">%d.%d.%d.%d %s</a></H4>""" % (headingname,num,section, subsection, subsubsection, prevheadingtext))
if subsubsubsection:
index += "</ul>\n"
if subsubsection == 1:
index += "<ul>\n"
index += """<li><a href="#%s">%s</a>\n""" % (headingname,prevheadingtext)
subsubsubsection = 0
skipspace = 1
continue
m = h5.match(s)
if m:
prevheadingtext = getheadingtext(m, s)
nameindex += 1
subsubsubsection += 1
headingname = getheadingname(m)
result.append("""<H5><a name="%s">%d.%d.%d.%d.%d %s</a></H5>""" % (headingname,num,section, subsection, subsubsection, subsubsubsection, prevheadingtext))
if subsubsubsection == 1:
index += "<ul>\n"
index += """<li><a href="#%s">%s</a>\n""" % (headingname,prevheadingtext)
skipspace = 1
continue
result.append(s)
if subsubsubsection:
index += "</ul>\n"
if subsubsection:
index += "</ul>\n"
if subsection:
index += "</ul>\n"
if section:
index += "</ul>\n"
index += "</div>\n<!-- INDEX -->\n"
data = "\n".join(result)
data = data.replace("@INDEX@",index) + "\n";
# Write the file back out
open(filename,"w").write(data)
# Print the TOC data to stdout correcting the anchor links for external referencing
index = index.replace("<li><a href=\"#","<li><a href=\"%s#" % filename)
print """<h3><a href="%s#%s">%d %s</a></h3>\n""" % (filename,filenamebase,num,name)
print index
|
