From: Mart Lubbers <mart@martlubbers.net>
Date: Mon, 2 Jun 2014 14:06:06 +0000 (+0200)
Subject: euao
X-Git-Url: https://git.martlubbers.net/?a=commitdiff_plain;h=65c4edb0769d9f9c78730f230a5ba7287c59a344;p=bsc-thesis1415.git

euao
---

diff --git a/program/hypconvert/hypconvert.py b/program/hypconvert/hypconvert.py
index 34548ff..b93f6fd 100644
--- a/program/hypconvert/hypconvert.py
+++ b/program/hypconvert/hypconvert.py
@@ -8,7 +8,10 @@ import re
 re_hdr = re.compile('<th>(?P<h>.*?)</th>')
 re_row = re.compile('<tr>(?P<row>.*?)</tr>')
 re_cel = re.compile('<td>(?P<c>.*?)</td>')
-re_spa = re.compile('(?P<b><span.*?background-color:(?P<c>.*?);.*?>)(?P<content>.*?)(?P<e></span>)')
+re_spa = re.compile('(?P<b><span.*?background-color:\s*(?P<c>.*?);.*?>)(?P<c' +
+                    'ontent>.*?)(?P<e></span>)')
+
+colordict = {'green': 'wat', 'blue': 'waar', 'red': 'wanneer'}
 
 
 def structure_data(d):
@@ -31,9 +34,12 @@ def parse_line(line):
         logging.debug('parsing column: {}'.format(column))
         markings = list(re_spa.finditer(column))
         if markings:
+            markings = [(colordict[m.group('c')], m.span('content'))
+                        for m in markings]
             results.append(markings)
             logging.debug('found {} spans in the column'.format(len(markings)))
     logging.debug('found {} columns with markings'.format(len(results)))
+    return results
 
 
 def main():
@@ -51,8 +57,10 @@ def main():
     logging.info('raw data parsed, going to structure data')
     structure_data(d)
     logging.info('data structured, parsed headers: {}'.format(d['headers']))
-    for line in filter(None, d['content']):
-        parse_line(line)
+    # Isolate the span objects from the lines and columns
+    lines = filter(None, d['content'])
+    matches = [(line, parse_line(line)) for line in lines if parse_line(line)]
+    pprint.pprint(matches)
 
 
 if __name__ == '__main__':