| 1 |
#!/usr/bin/env python2 |
| 2 |
import sys |
| 3 |
from string import join, strip, split |
| 4 |
import getopt |
| 5 |
|
| 6 |
from xml.sax import saxexts |
| 7 |
from xml.sax.saxlib import HandlerBase |
| 8 |
from xml.dom.minidom import parse, Element, Text |
| 9 |
|
| 10 |
from textformatter import TextFormatter |
| 11 |
|
| 12 |
|
| 13 |
class Options: |
| 14 |
|
| 15 |
new_sgml_dtd = 0 |
| 16 |
|
| 17 |
|
| 18 |
def extract_raw_text(element): |
| 19 |
text = [] |
| 20 |
for child in element.childNodes: |
| 21 |
if child.nodeName == '#text': |
| 22 |
text.append(child.nodeValue) |
| 23 |
else: |
| 24 |
text.extend(extract_raw_text(child)) |
| 25 |
return join(text, '') |
| 26 |
|
| 27 |
def element_to_sgml(element, label_dict = {}): |
| 28 |
text = [] |
| 29 |
#print 'element_to_sgml', element |
| 30 |
for child in element.childNodes: |
| 31 |
#print child |
| 32 |
if child.nodeName == 'faqref': |
| 33 |
ref = "FAQ" + child.getAttribute("id") |
| 34 |
item = label_dict[ref] |
| 35 |
t = '<ref id="%s">%s.%s</>' % (ref, item.section, item.num) |
| 36 |
elif child.nodeName == 'url': |
| 37 |
url = child.getAttribute("url") |
| 38 |
t = '<href url="%s">%s</>' % (url, url) |
| 39 |
elif child.nodeName == 'href': |
| 40 |
url = child.getAttribute("url") |
| 41 |
t = '<href url="%s">' % url |
| 42 |
t = t + extract_raw_text(child) + "</>" |
| 43 |
elif child.nodeName == 'p': |
| 44 |
t = '\n\n' |
| 45 |
else: |
| 46 |
t = child.toxml() |
| 47 |
text.append(t) |
| 48 |
return join(text, '') |
| 49 |
|
| 50 |
def element_to_xhtml(element, label_dict = {}): |
| 51 |
text = [] |
| 52 |
for child in element.childNodes: |
| 53 |
#print child |
| 54 |
if child.nodeName == 'faqref': |
| 55 |
ref = "FAQ" + child.getAttribute("id") |
| 56 |
item = label_dict[ref] |
| 57 |
t = '<a href="#%s">%s.%s</a>' % (ref, item.section, item.num) |
| 58 |
elif child.nodeName == 'url': |
| 59 |
url = child.getAttribute("url") |
| 60 |
t = '<a href="%s">%s</a>' % (url, url) |
| 61 |
elif child.nodeName == 'href': |
| 62 |
url = child.getAttribute("url") |
| 63 |
t = '<a href="%s">' % url |
| 64 |
t = t + extract_raw_text(child) + "</a>" |
| 65 |
elif child.nodeName == 'p': |
| 66 |
t = '<p>' |
| 67 |
t = t + element_to_xhtml(child, label_dict) |
| 68 |
t = t + '</p>' |
| 69 |
elif child.nodeName == 'itemize': |
| 70 |
ul = Element("ul") |
| 71 |
for item in child.getElementsByTagName("item"): |
| 72 |
li = Element("li") |
| 73 |
for insideitem in item.childNodes: |
| 74 |
li.appendChild(insideitem) |
| 75 |
ul.appendChild(li) |
| 76 |
t = ul.toxml() |
| 77 |
else: |
| 78 |
t = child.toxml() |
| 79 |
text.append(t) |
| 80 |
return join(text, '') |
| 81 |
|
| 82 |
class Entry: |
| 83 |
|
| 84 |
def __init__(self, section, num, title, body, label = ''): |
| 85 |
self.section = section |
| 86 |
self.num = num |
| 87 |
self.title = title |
| 88 |
self.body = body |
| 89 |
if label: |
| 90 |
self.label = "FAQ" + label |
| 91 |
else: |
| 92 |
self.label = "FAQ" + `self.section` + '.' + `self.num` |
| 93 |
|
| 94 |
def __cmp__(self, other): |
| 95 |
if self.section != other.section: |
| 96 |
return cmp(self.section, other.section) |
| 97 |
return cmp(self.num, other.num) |
| 98 |
|
| 99 |
def save_as_sgml(self, file, labeldict): |
| 100 |
if Options.new_sgml_dtd: |
| 101 |
file.write('<faqentry id="%s">%d.%d %s\n' % |
| 102 |
(self.label, self.section, self.num, |
| 103 |
element_to_sgml(self.title))) |
| 104 |
else: |
| 105 |
file.write('<faqentry>%d.%d %s\n<label id="%s">\n' |
| 106 |
% (self.section, self.num, element_to_sgml(self.title), |
| 107 |
self.label)) |
| 108 |
file.write("<faqbody>\n") |
| 109 |
file.write(element_to_sgml(self.body, labeldict)) |
| 110 |
file.write("</faqbody>\n</faqentry>\n") |
| 111 |
|
| 112 |
def toc_sgml(self): |
| 113 |
return ' %3d.%d <ref id="%s">%s</>' % \ |
| 114 |
(self.section, self.num, self.label, |
| 115 |
element_to_sgml(self.title)) |
| 116 |
|
| 117 |
def save_as_xhtml(self, file, labeldict): |
| 118 |
file.write('<h3><a name="%s">%d.%d %s</a></h3>\n' % |
| 119 |
(self.label, self.section, self.num, |
| 120 |
element_to_xhtml(self.title))) |
| 121 |
|
| 122 |
paragraphs = 0 |
| 123 |
if len(self.body.getElementsByTagName("p")): |
| 124 |
file.write(element_to_xhtml(self.body, labeldict)) |
| 125 |
else: |
| 126 |
file.write("<p>\n") |
| 127 |
file.write(element_to_xhtml(self.body, labeldict)) |
| 128 |
file.write("</p>\n") |
| 129 |
|
| 130 |
def toc_xhtml(self): |
| 131 |
return ' %3d.%d <a href="#%s">%s</a>' % \ |
| 132 |
(self.section, self.num, self.label, |
| 133 |
element_to_xhtml(self.title)) |
| 134 |
|
| 135 |
def toc_text(self): |
| 136 |
title = extract_raw_text(self.title) |
| 137 |
title = join(split(title)) |
| 138 |
return '%3d.%d %s' % (self.section, self.num, title) |
| 139 |
|
| 140 |
|
| 141 |
class Section: |
| 142 |
|
| 143 |
def __init__(self, section, title, label = ''): |
| 144 |
#print 'Section', section, title, `label` |
| 145 |
self.section = section |
| 146 |
self.title = title |
| 147 |
self.entries = [] |
| 148 |
if label: |
| 149 |
self.label = "FAQ" + label |
| 150 |
else: |
| 151 |
self.label = "FAQ" + `self.section` |
| 152 |
|
| 153 |
def append(self, entry): |
| 154 |
self.entries.append(entry) |
| 155 |
|
| 156 |
def save_as_sgml(self, file, labeldict): |
| 157 |
if Options.new_sgml_dtd: |
| 158 |
file.write('<faqsect id="%s">%d %s\n' % |
| 159 |
(self.label, self.section, element_to_sgml(self.title))) |
| 160 |
else: |
| 161 |
file.write('<faqsect>%d %s\n<label id="%s">\n' % |
| 162 |
(self.section, element_to_sgml(self.title), self.label)) |
| 163 |
for entry in self.entries: |
| 164 |
entry.save_as_sgml(file, labeldict) |
| 165 |
file.write("</faqsect>\n") |
| 166 |
|
| 167 |
def toc_sgml(self): |
| 168 |
return '%3d <ref id="%s">%s</>' % (self.section, self.label, |
| 169 |
element_to_sgml(self.title)) |
| 170 |
def save_as_xhtml(self, file, labeldict): |
| 171 |
file.write('<h2><a name="%s">%d %s</a></h2>\n' % |
| 172 |
(self.label, self.section, element_to_xhtml(self.title))) |
| 173 |
for entry in self.entries: |
| 174 |
entry.save_as_xhtml(file, labeldict) |
| 175 |
|
| 176 |
def toc_xhtml(self): |
| 177 |
return '%3d <a href="#%s">%s</a>' % (self.section, self.label, |
| 178 |
element_to_xhtml(self.title)) |
| 179 |
def toc_text(self): |
| 180 |
title = extract_raw_text(self.title) |
| 181 |
title = join(split(title)) |
| 182 |
return '%3d %s' % (self.section, title) |
| 183 |
|
| 184 |
|
| 185 |
|
| 186 |
def extract(domfaqlist): |
| 187 |
result = [] |
| 188 |
label_dict = {} |
| 189 |
faq_title = domfaqlist.getElementsByTagName('title')[0] |
| 190 |
domsections = domfaqlist.getElementsByTagName('section') |
| 191 |
for secnum in range(len(domsections)): |
| 192 |
section = Section(secnum + 1, |
| 193 |
domsections[secnum].getElementsByTagName('title')[0], |
| 194 |
label = domsections[secnum].getAttribute('id')) |
| 195 |
result.append(section) |
| 196 |
secfaqs = domsections[secnum].getElementsByTagName('faq') |
| 197 |
for faqnum in range(len(secfaqs)): |
| 198 |
title = secfaqs[faqnum].getElementsByTagName('title')[0] |
| 199 |
body = secfaqs[faqnum].getElementsByTagName('body')[0] |
| 200 |
label = secfaqs[faqnum].getAttribute('id') |
| 201 |
entry = Entry(secnum + 1, faqnum + 1, title, body, |
| 202 |
label = label) |
| 203 |
if label: |
| 204 |
label_dict[entry.label] = entry |
| 205 |
section.append(entry) |
| 206 |
return result, label_dict, faq_title |
| 207 |
|
| 208 |
|
| 209 |
sgml_header = ''' |
| 210 |
<faqlist> |
| 211 |
<faqhead1>Table of Contents</faqhead1> |
| 212 |
''' |
| 213 |
|
| 214 |
xhtml_header = '''\ |
| 215 |
title: Skencil / Frequently Asked Questions |
| 216 |
|
| 217 |
<h2>Table of Contents</h2> |
| 218 |
''' |
| 219 |
|
| 220 |
|
| 221 |
def write_sgml(file, faqlist, title, label_dict): |
| 222 |
file.write("<faqlist>\n<faqtoc>\n") |
| 223 |
for section in faqlist: |
| 224 |
file.write(section.toc_sgml()) |
| 225 |
file.write('<newline>\n') |
| 226 |
for entry in section.entries: |
| 227 |
file.write(entry.toc_sgml()) |
| 228 |
file.write('<newline>\n') |
| 229 |
file.write("</faqtoc>\n") |
| 230 |
|
| 231 |
for section in faqlist: |
| 232 |
section.save_as_sgml(file, label_dict) |
| 233 |
file.write("</faqlist>") |
| 234 |
|
| 235 |
def write_xhtml(file, faqlist, title, label_dict): |
| 236 |
file.write(xhtml_header) |
| 237 |
for section in faqlist: |
| 238 |
file.write(section.toc_xhtml()) |
| 239 |
file.write('<br />\n') |
| 240 |
for entry in section.entries: |
| 241 |
file.write(entry.toc_xhtml()) |
| 242 |
file.write('<br />\n') |
| 243 |
|
| 244 |
for section in faqlist: |
| 245 |
section.save_as_xhtml(file, label_dict) |
| 246 |
|
| 247 |
|
| 248 |
bullets = '-+o*' |
| 249 |
def format_element(element, formatter, label_dict, list_depth = -1): |
| 250 |
for child in element.childNodes: |
| 251 |
#print child |
| 252 |
if child.nodeName == 'faqref': |
| 253 |
ref = "FAQ" + child.getAttribute("id") |
| 254 |
item = label_dict[ref] |
| 255 |
formatter.add_text('%s.%s' % (item.section, item.num)) |
| 256 |
elif child.nodeName == 'url': |
| 257 |
url = child.getAttribute("url") |
| 258 |
formatter.add_text('URL:%s' % url) |
| 259 |
elif child.nodeName == 'href': |
| 260 |
url = child.getAttribute("url") |
| 261 |
text = extract_raw_text(child) |
| 262 |
formatter.add_text('%s (URL:%s)' % (text, url)) |
| 263 |
elif child.nodeName == 'p': |
| 264 |
formatter.new_paragraph() |
| 265 |
format_element(child, formatter, label_dict, list_depth) |
| 266 |
elif child.nodeName == 'itemize': |
| 267 |
formatter.new_paragraph(indent = 4) |
| 268 |
format_element(child, formatter, label_dict, |
| 269 |
list_depth = list_depth + 1) |
| 270 |
formatter.new_paragraph() |
| 271 |
formatter.outdent(4) |
| 272 |
elif child.nodeName == 'item': |
| 273 |
formatter.new_paragraph(bullet = bullets[list_depth]) |
| 274 |
format_element(child, formatter, label_dict, list_depth) |
| 275 |
elif child.nodeName == '#text': |
| 276 |
formatter.add_text(child.nodeValue) |
| 277 |
else: |
| 278 |
format_element(child, formatter, label_dict, |
| 279 |
list_depth = list_depth) |
| 280 |
|
| 281 |
def write_text(file, faqlist, title, label_dict): |
| 282 |
formatter = TextFormatter(file) |
| 283 |
formatter.heading(extract_raw_text(title), underline = '=') |
| 284 |
formatter.indent(2) |
| 285 |
for section in faqlist: |
| 286 |
formatter.vspace(1) |
| 287 |
formatter.paragraph(section.toc_text(), vspace = 0) |
| 288 |
for entry in section.entries: |
| 289 |
formatter.paragraph(entry.toc_text(), vspace = 0) |
| 290 |
formatter.outdent(2) |
| 291 |
|
| 292 |
for section in faqlist: |
| 293 |
formatter.vspace(2) |
| 294 |
formatter.heading(section.toc_text(), underline = '=') |
| 295 |
for entry in section.entries: |
| 296 |
formatter.vspace(1) |
| 297 |
formatter.heading(entry.toc_text(), underline = '-') |
| 298 |
formatter.vspace(1) |
| 299 |
format_element(entry.body, formatter, label_dict) |
| 300 |
|
| 301 |
formatter.close() |
| 302 |
|
| 303 |
def main(): |
| 304 |
format = 'sgml' |
| 305 |
|
| 306 |
opts, args = getopt.getopt(sys.argv[1:], "ntx") |
| 307 |
for opt, value in opts: |
| 308 |
if opt == '-t': |
| 309 |
format = 'text' |
| 310 |
elif opt == '-n': |
| 311 |
Options.new_sgml_dtd = 1 |
| 312 |
elif opt == '-x': |
| 313 |
format = 'xhtml' |
| 314 |
|
| 315 |
if len(args) == 0: |
| 316 |
print 'faqdom.py usage: python faqdom.py [-t|-x] [-n] <xml_file> [<outfile>].' |
| 317 |
return |
| 318 |
|
| 319 |
doc = parse(args[0]) |
| 320 |
faqlist, label_dict, title = extract(doc.getElementsByTagName("faqlist")[0]) |
| 321 |
if len(args) > 1: |
| 322 |
outfile = open(args[1], "w") |
| 323 |
else: |
| 324 |
outfile = sys.stdout |
| 325 |
|
| 326 |
if format == 'sgml': |
| 327 |
write_sgml(outfile, faqlist, title, label_dict) |
| 328 |
elif format == 'text': |
| 329 |
write_text(outfile, faqlist, title, label_dict) |
| 330 |
elif format == 'xhtml': |
| 331 |
write_xhtml(outfile, faqlist, title, label_dict) |
| 332 |
|
| 333 |
main() |
| 334 |
|
Parent Directory
| 
Revision Log