embee/pyaccuwage
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

update for 2023 p1220 parsing, stupid irs

Browse source
This commit is contained in:
Mark Riedesel 2024-03-29 10:46:01 -04:00
parent 86f8861da1
commit 66573e4d1d
3 changed files with 97 additions and 346 deletions
Download patch file Download diff file Expand all files Collapse all files

51
scripts/pyaccuwage-pdfparse
View file

@ -1,4 +1,4 @@
#!/usr/bin/python
#!/usr/bin/env python
from pyaccuwage.parser import RecordBuilder
from pyaccuwage.pdfextract import PDFRecordFinder
import argparse
@ -29,48 +29,9 @@ doc = PDFRecordFinder(source_file)
records = doc.records()
builder = RecordBuilder()
def record_begins_at(field):
return int(fields[0].data.values()[0].split('-')[0], 10)
def record_ends_at(fields):
return int(fields[-1].data.values()[0].split('-')[-1], 10)
last_record_begins_at = -1
last_record_ends_at = -1
for rec in records:
#if not rec[1]:
# continue # no actual fields detected
fields = rec[1]
# strip out fields that are not 4 items long
fields = filter(lambda x:len(x.tuple) == 4, fields)
# strip fields that don't begin at position 0
fields = filter(lambda x: 0 in x.data, fields)
# strip fields that don't have a length-range type item in position 0
fields = filter(lambda x: re.match('^\d+[-]?\d*$', x.data[0]), fields)
if not fields:
continue
begins_at = record_begins_at(fields)
ends_at = record_ends_at(fields)
# FIXME record_ends_at is randomly exploding due to record data being
# a lump of text and not necessarily a field entry. I assume
# this is cleaned out by the record builder class.
#print last_record_ends_at + 1, begins_at
if last_record_ends_at + 1 != begins_at:
name = re.sub('^[^a-zA-Z]*','',rec[0].split(':')[-1])
name = re.sub('[^\w]*', '', name)
sys.stdout.write("\nclass %s(pyaccuwagemodel.Model):\n" % name)
for field in builder.load(map(lambda x:x.tuple, rec[1][0:])):
for (name, fields) in records:
name = re.sub(r'^[^a-zA-Z]*','', name.split(':')[-1])
name = re.sub(r'[^\w]*', '', name)
sys.stdout.write("\nclass %s(pyaccuwagemodel.Model):\n" % name)
for field in builder.load(map(lambda x: x, fields[0:])):
sys.stdout.write('\t' + field + '\n')
#print field
last_record_ends_at = ends_at