Rihards Gailums
71250e7b0e
Loģisks budžeta modelis (Source, Provision, Parameter, Actor, Purpose, Indicator, Rule, ClassItem, Allocation), nevis likuma pielikumu izkārtojuma kopija. Abi likumi: teksts un visi 12 pielikumi. Atpakaļsaderība: 2026 — 58 457 no 58 457, 2025 — 55 677 no 55 677 pielikumos drukāto skaitļu atjaunoti tikai no XML. Avoti (likumi.lv, klasifikāciju MK noteikumi), rīki, datu līgums B15, dokumentācija. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016679RwmHsuTFfxt26wP6rk
56 lines
2.4 KiB
Python
56 lines
2.4 KiB
Python
"""Shared readers for budget-law annex files (xlsx via openpyxl, xls via xlrd, docx via stdlib)."""
|
|
import zipfile, re, xml.etree.ElementTree as ET
|
|
|
|
def sheets(path):
|
|
"""Yield (sheet_name, rows) with rows as lists of stripped strings/numbers; hidden BEx sheets included."""
|
|
if path.lower().endswith('.xlsx'):
|
|
import openpyxl
|
|
wb = openpyxl.load_workbook(path, read_only=True, data_only=True)
|
|
for ws in wb.worksheets:
|
|
rows = []
|
|
for r in ws.iter_rows(values_only=True):
|
|
rows.append([("" if v is None else (v.strip() if isinstance(v, str) else v)) for v in r])
|
|
yield ws.title, rows
|
|
elif path.lower().endswith('.xls'):
|
|
import xlrd
|
|
wb = xlrd.open_workbook(path)
|
|
for ws in wb.sheets():
|
|
rows = []
|
|
for i in range(ws.nrows):
|
|
rows.append([(c.strip() if isinstance(c, str) else c) for c in ws.row_values(i)])
|
|
yield ws.name, rows
|
|
|
|
def main_sheet(path):
|
|
"""The printed annex sheet: the one whose name ends with 'piel' or is the first non-BEx sheet with most rows."""
|
|
best = None
|
|
for name, rows in sheets(path):
|
|
if name.lower().endswith('piel') or re.match(r'^\d+\.?\s*piel', name.lower()):
|
|
return name, rows
|
|
if name.startswith(('BEx', 'HEADER', 'FOOTER', 'ZQZ', 'var', 'list', 'parms')):
|
|
continue
|
|
if best is None or len(rows) > len(best[1]):
|
|
best = (name, rows)
|
|
return best
|
|
|
|
W = '{http://schemas.openxmlformats.org/wordprocessingml/2006/main}'
|
|
def docx_tables(path):
|
|
"""List of tables, each a list of rows of cell texts."""
|
|
x = ET.fromstring(zipfile.ZipFile(path).read('word/document.xml'))
|
|
out = []
|
|
for t in x.iter(W + 'tbl'):
|
|
rows = []
|
|
for tr in t.findall(W + 'tr'):
|
|
rows.append([''.join(n.text or '' for n in tc.iter(W + 't')).strip() for tc in tr.findall(W + 'tc')])
|
|
out.append(rows)
|
|
return out
|
|
|
|
def docx_paras(path):
|
|
x = ET.fromstring(zipfile.ZipFile(path).read('word/document.xml'))
|
|
return [''.join(n.text or '' for n in p.iter(W + 't')).strip() for p in x.iter(W + 'p')]
|
|
|
|
def num(v):
|
|
"""Parse an amount cell: numbers, '1 234 567', '-1 234', '–'. Returns float or None."""
|
|
if isinstance(v, (int, float)): return float(v)
|
|
s = str(v).replace(' ', ' ').replace(' ', '').replace('–', '-').replace('−', '-').replace(',', '.')
|
|
return float(s) if re.fullmatch(r'-?\d+(\.\d+)?', s) else None
|