def __init__(self, path):
"""
self.unit - the unit to which this Chapter belongs (e.g., 'Pathways & Advance Engineering')
self.data - TabData instances for each topic
"""
self.data = []
s = utils.getHtml(path)
filename = os.path.basename(path)
self.unit = os.path.basename(os.path.dirname(path))
self.num, self.chapter = self.getChapterInfo(filename)
tagPat = RegExUtils.getTagPattern('x:ExcelWorkbook')
m = tagPat.search(s)
if not m:
raise Exception, "could not get TABS data from file (%s)" % path
print 'found data'
xml = m.group(0).replace('x:', '') # strip x prefix from all elements
rec = XmlRecord(xml=xml)
rec.xpath_delimiter = '/'
tabNodes = rec.selectNodes(
rec.dom, "ExcelWorkbook/ExcelWorksheets/ExcelWorksheet")
# we ignore the 'Cover sheet'
print 'creating %d tabs' % len(tabNodes)
for tabElement in tabNodes:
tabData = TabData(tabElement, self.unit)
if tabData.name.lower() != 'cover sheet':
tabData.num = len(self) + 1
self.append(tabData)
def pp (self):
"""
use
"""
tagPat = self.getTagPat()
i = 0 # index into the original xml
s = self.rec.__repr__()
print "pp processing %d lines" % len (s.split('\n'))
reps = 0
buff = ""
while i <= len(s):
m = tagPat.search (s,i)
if m is None:
buff += s[i:]
i = len(s)
# print 'pattern not found'
break
else:
j = m.start()
buff += s[i:j]
# print 'pattern found (%d): "%s"' % (j, m.group(1))
tag = m.group(1)
tagSet = RegExUtils.getTagPattern (tag).match(s, j)
if tagSet:
# print tagSet.group(1) # this is the content of this tagSet
if self.isLeaf (tagSet):
# print "%s is a leaf" % tag
fixedLeaf = self.fixLeaf (tagSet)
# print 'fixed leaf: "%s"' % fixedLeaf
buff += fixedLeaf
i=tagSet.end()
else:
## print "%s is NOT a leaf" % tag
buff += s[j]
i = j + 1
else:
# we have an empty tag (e.g., <children/>), just add it to buff and continue
buff += m.group()
i = j + len(m.group())
## print 'set i to %d' % i
reps += 1
if reps % 10 == 0:
# print dot every once in a while to show progress
sys.__stderr__.write('.')
# print "%d/%d" % (i, len(s))
if reps > 50000:
print "breaking because limit has been reached!"
sys.exit()
return '<?xml version="1.0" encoding="UTF-8" ?>\n%s' % buff.strip()
def removeFontTags(content):
out = ""
i = 0
# tag = "FONT"
# patStr = "<%s.*?>(.*?)</%s>" % (tag, tag)
# tagPat = re.compile (patStr, re.DOTALL)
tagPat = RegExUtils.getTagPattern("FONT")
while i < len(content):
m = tagPat.match(content[i:])
if not m:
out = out + content[i]
i = i + 1
continue
out = out + m.group(1)
i = i + m.end()
return out
def getTopicData(self, path):
"""
read an html file
extract a table containing topicData
use the table data to instantiate a TopPickData instance
"""
html = utils.getHtml(path)
tablePat = RegExUtils.getTagPattern('table')
m = tablePat.search(html)
if not m:
raise Exception, "Data Table not found!"
xml = m.group()
# xml = stripConditionals (xml)
xml = utils.xcelHtml2Xml(xml)
# print xml
return TopicRecord(xml).parsed_data
import sys, re
from serviceclient import SimpleClient
from JloXml import RegExUtils as rexml
h2Tag_pat = rexml.getTagPattern ('h2')
attr_pat = rexml.attrPattern('name')
a_pat = rexml.getTagPattern('a')
def get_modules(url):
client = SimpleClient (url)
html = client.getData()
m = h2Tag_pat.findall(html)
modules = []
if 0 and m:
print 'm is TRUE'
print ' there are %d in m' % len(m)
print 'the first element is a %s' % type (m[0])
if not m:
return []
for s in m:
m2 = attr_pat.match (s)
if not m2:
print 'getHtml() encoding: %s' % myEncoding
print ' path:', path
html = codecs.open(path, 'r', myEncoding).read()
# html = open(path,'r').read()
lines = html.split(linesep)
if verbose:
print '%d lines read' % len(lines)
if linesep == '\r':
print 'spliting on mac NL'
html = u'\n'.join(lines)
return html
condPat = re.compile('<!\[if[\s]+.*?<!\[endif\]>', re.DOTALL)
hrefPat = RegExUtils.attrPattern("href")
tagPat = re.compile('<([^\s^/^<]+)[\s]*?[^<]*?>',
re.DOTALL) # matches opening tag (e.g., '<table ...>'
htmlCommentPat = re.compile('<!--.*?-->', re.DOTALL)
def xcelHtml2Xml(html):
"""
clean up the html so it can be processed as XML.
this involves stripping attributes, which often are not quoted
"""
clean = ""
i = 0
while i < len(html):
ch = html[i]