Binh Nguyen
1c7533973a
to track the beginning/ending points for each record and append continuation records onto the previous. There's some issue in the pyaccuwage-pdfparse script causing it to have problems reading the last record field in a record group. Maybe the record extractor needs to dump the last failed ColumnCollector rather than return it if it's determined to hold junk data? The record builder seems to handle everything just fine. Added a function to the field name parsing to replace ampersands with an "and" string so as not to cause problems with variable names.
54 lines
1.7 KiB
Python
Executable file
54 lines
1.7 KiB
Python
Executable file
#!/usr/bin/python
|
|
from pyaccuwage.parser import RecordBuilder
|
|
from pyaccuwage.pdfextract import PDFRecordFinder
|
|
import argparse
|
|
import sys
|
|
import os
|
|
import re
|
|
|
|
parser = argparse.ArgumentParser(description="Parse and convert contents of IRS files into pyaccuwage e-file classes.")
|
|
parser.add_argument("-i", "--input", nargs=1, required=True, metavar="file", type=argparse.FileType('r'), help="Source PDF file, ie: p1220.pdf")
|
|
parser.add_argument("-f", "--full", help="Generate full python file, including related imports.", action="store_true")
|
|
|
|
args = parser.parse_args()
|
|
|
|
def generate_imports():
|
|
return "\n".join([
|
|
"from pyaccuwage import model",
|
|
"from pyaccuwage.fields import *",
|
|
"",
|
|
"",
|
|
])
|
|
|
|
def generate_class_begin(name):
|
|
return "class %s(mode.Model):\n" % name
|
|
|
|
if args.full:
|
|
sys.stdout.write(generate_imports())
|
|
|
|
source_file = os.path.abspath(args.input[0].name)
|
|
|
|
doc = PDFRecordFinder(source_file)
|
|
records = doc.records()
|
|
builder = RecordBuilder()
|
|
|
|
def record_begins_at(record):
|
|
return int(record[1][1].data.values()[0].split('-')[0], 10)
|
|
|
|
def record_ends_at(record):
|
|
return record[1][-1].data
|
|
return int(record[1][-1].data.values()[0].split('-')[-1], 10)
|
|
|
|
for rec in records:
|
|
|
|
print record_begins_at(rec) #, 'to', record_ends_at(rec)
|
|
# 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.
|
|
|
|
sys.stdout.write("class %s(object):\n" % re.sub('[^\w]','',rec[0]))
|
|
|
|
for field in builder.load(map(lambda x:x.tuple, rec[1][1:])):
|
|
sys.stdout.write('\t' + field + '\n')
|
|
#print field
|
|
|