stupidcomputer/yig
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix bill parsing in the main parser

Browse Source
This commit is contained in:
stupidcomputer 2024-05-19 16:02:03 -05:00
parent 11fbcb474a
commit dbd9632e16
1 changed files with 15 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
parsers.py
View File

@ -155,20 +155,27 @@ class HSYIGPdfParser:
def _pretty_print_bill_text(self, bill_text: str): def _pretty_print_bill_text(self, bill_text: str):
replaced = bill_text.replace("<EFBFBD>", "\n") replaced = bill_text.replace("<EFBFBD>", "\n")
replaced = bill_text
replaced = replaced.split('\n') replaced = replaced.split('\n')
replaced = [
replaced = [i.rstrip().lstrip() for i in replaced] i \
.replace('<EFBFBD>', ' ') \
.rstrip() \
.lstrip() \
for i in replaced
]
first_line_number = self._find_first_line_number(replaced) first_line_number = self._find_first_line_number(replaced)
title = ' '.join(replaced[:(first_line_number - 1)])
title = ' '.join(replaced[:first_line_number]) title = ' '.join(title.split()) # remove double spaces
rebuilt = replaced[first_line_number:][1::2] rebuilt = replaced[first_line_number:][1::2]
# remove the last line number, it doesn't have a cooresponding space at the end
rebuilt = rebuilt[:-1]
# remove the first line, as it's the whitespace between the title and the bill text
rebuilt = rebuilt[1:]
return { return {
"title": title.lstrip(), "title": title.lstrip(),
"bill_array": rebuilt "bill_array": rebuilt
} }
@classmethod
def from_filename(cls, filename: str) -> Any: # TODO: fix this so it shows PdfParser
return cls(fitz.open(filename))