146 # parser = html5lib.HTMLParser(tree=treebuilders.getTreeBuilder("beautifulsoup")) |
146 # parser = html5lib.HTMLParser(tree=treebuilders.getTreeBuilder("beautifulsoup")) |
147 # html = parser.parse(htmlcontent.encode("utf8"), encoding="utf8") |
147 # html = parser.parse(htmlcontent.encode("utf8"), encoding="utf8") |
148 html = get_the_soup(htmlcontent) ; |
148 html = get_the_soup(htmlcontent) ; |
149 |
149 |
150 # import pdb;pdb.set_trace() |
150 # import pdb;pdb.set_trace() |
151 |
151 if comments : |
152 max_wrapper = max([comment.end_wrapper for comment in comments]) |
152 max_wrapper = max([comment.end_wrapper for comment in comments]) |
153 min_wrapper = min([comment.start_wrapper for comment in comments]) |
153 min_wrapper = min([comment.start_wrapper for comment in comments]) |
154 |
154 |
155 datas = {} # { wrapper_id : {'start_color':nb_of_comments_unterminated_at_wrapper_start, 'offsets':{offset: [[ids of wrappers starting at offset], [ids of wrappers ending at offset]]}} |
155 datas = {} # { wrapper_id : {'start_color':nb_of_comments_unterminated_at_wrapper_start, 'offsets':{offset: [[ids of wrappers starting at offset], [ids of wrappers ending at offset]]}} |
156 # datas['offsets'][someoffset][0] and idem[1] will be ordered the way comments are (should be ('start_wrapper', 'start_offset', 'end_wrapper', 'end_offset') important) |
156 # datas['offsets'][someoffset][0] and idem[1] will be ordered the way comments are (should be ('start_wrapper', 'start_offset', 'end_wrapper', 'end_offset') important) |
157 cpt = 1 # starting numbered comment |
157 cpt = 1 # starting numbered comment |
158 for comment in comments : |
158 for comment in comments : |
159 if comment.is_reply() : |
159 if comment.is_reply() : |