[Doitsu]

Originally Posted by KevinH

Hi Doitsu,

I have slightly modified your GumboOffset example to do what we do inside Sigil to make it more general

import sigil_gumbo_bs4_adapter as gumbo_bs4

wspace = (" ", "\n", "\r", "\t", "\v" "\f")

def preprocess(src):
    newsrc = src
    line_offset = 0;
    pos_offset = 0;
    n = len(src)
    if src.startswith("<?xml"):
        # remove any xml header line and trailing whitespace
        end = src.find('>',5)
        if end != -1:
            end = end + 1
            while end < n and src[end:end+1] in wspace:
                if src[end:end+1] == "\n":
                    line_offset += 1
                end += 1
        if (end < n):
            pos_offset = end
            newsrc = src[end:]
    return (newsrc, line_offset, pos_offset)

 
def run(bk):
    for id_type, id in bk.selected_iter():
        filename =  os.path.basename(bk.id_to_href(id))
        html = bk.readfile(id).replace('\r\n', '\n')
        (html, line_offset, pos_offset)  = preprocess(html)
        soup = gumbo_bs4.parse(html)
        
        for para in soup.find_all('p'):
            linenumber = para.line + line_offset
            colnumber = para.col
            offset =  para.offset + pos_offset
            message = escape(str(para)).replace('"', "&quot;")
            bk.add_extended_result('info', filename, linenumber, offset, 'Line: ' + str(linenumber) + ' Col: ' + str(colnumber) + ' Gumbo method: ' + message)
        
    return 0
        
def main():
    print('I reached main when I should not have\n')
    return -1

if __name__ == "__main__":
    sys.exit(main())

We could even move your replace "\r\n" with "\n" inside the new "preprocess" routine if so desired to make the preprocess routine better match how text is parsed and handled inside Sigil.

Thanks for the updated code, I'll check it out tomorrow.