Files
doc_build/lib/jsonFromXlsx.py

304 lines
11 KiB
Python

"""Builds a JSON hierarchy tree from the Position column of an Excel Stk.-Liste.
Usage:
python jsonFromXlsx.py --filename Fortna --tab soll
python jsonFromXlsx.py --filename Fortna --tab ist --output result.json
python jsonFromXlsx.py --all
"""
import argparse
import json
import os
import re
import sys
from collections import Counter
from pathlib import Path
import openpyxl
SHEET_NAMES = {
"soll": "Stk.-Liste SOLL",
"ist": "Stk.-Liste IST",
}
# Patterns to match sheet names (case-insensitive), ordered by priority
# Matches: Stk.-Liste SOLL, Stck.-Liste Soll, Stückliste SOLL, Stk. Liste IST, etc.
SHEET_PATTERNS = {
"soll": [
re.compile(r"st[ck]+[\.\-]?\s*liste[n]?\s+soll", re.IGNORECASE),
re.compile(r"st[üu]ckliste[n]?\s+soll", re.IGNORECASE),
],
"ist": [
re.compile(r"st[ck]+[\.\-]?\s*liste[n]?\s+ist", re.IGNORECASE),
re.compile(r"st[üu]ckliste[n]?\s+ist", re.IGNORECASE),
],
}
# Column indices (0-based) in the header row
COL_POSITION = 0
COL_TEILENUMMER = 1
COL_BEZEICHNUNG = 2
COL_MENGE = 3
HEADER_ROW = 3 # 1-based row number of the header (minimum, actual may be later)
RE_POSITION = re.compile(r"^\d+(/\d+)*$") # valid position pattern: "10" or "10/5/1"
# Sivas numbers where Menge represents length (meters) instead of piece count
LAENGENABHAENGIG = {
"821106001", "821106002",
"825084000", "825084007",
"825104000", "825104007",
"825144000", "825144007",
"821006026", "821006034", "821006035", "821006045",
"825004000",
}
def find_xlsx(examples_dir: str, pattern: str) -> Path:
"""Find an .xlsx file in examples/ whose name contains the given pattern."""
matches = []
for f in Path(examples_dir).glob("*.xlsx"):
if pattern.lower() in f.name.lower():
matches.append(f)
if not matches:
print(f"FEHLER: Keine .xlsx-Datei mit Muster '{pattern}' in {examples_dir} gefunden.")
sys.exit(1)
if len(matches) > 1:
print(f"Mehrere Dateien gefunden fuer Muster '{pattern}':")
for m in sorted(matches):
print(f" {m.name}")
print(f"Verwende: {matches[0].name}")
return sorted(matches)[0]
def make_key(teilenummer: str, bezeichnung: str, is_unique: bool) -> str:
"""Build a node key from Teilenummer, adding Bezeichnung if not unique."""
if is_unique:
return teilenummer
combined = f"{teilenummer}-{bezeichnung}"
return combined.replace(" ", "_")
def unique_key(parent: dict, key: str) -> str:
"""Return key with _1, _2, ... suffix if it already exists in parent."""
if key not in parent:
return key
suffix = 1
while f"{key}_{suffix}" in parent:
suffix += 1
return f"{key}_{suffix}"
def build_tree(ws, sheet_type: str) -> dict:
"""Read the worksheet and build a nested dict from Position paths.
Keys are Teilenummer-based (with Bezeichnung if non-unique).
Position paths are used only for hierarchy, not as keys.
"""
# First pass: collect all Teilenummern to determine uniqueness
teil_counter: Counter = Counter()
rows_data = []
for row in ws.iter_rows(min_row=HEADER_ROW + 1, max_row=ws.max_row, values_only=True):
pos = row[COL_POSITION]
teil = row[COL_TEILENUMMER]
bez = row[COL_BEZEICHNUNG]
menge = row[COL_MENGE] if len(row) > COL_MENGE else None
if pos is None or teil is None:
continue
pos_str = str(pos).strip()
if not RE_POSITION.match(pos_str):
continue # skip header rows and non-position entries
teil_str = str(teil).strip()
bez_str = str(bez).strip() if bez else ""
try:
menge_val = float(menge) if menge is not None else 0.0
except (ValueError, TypeError):
menge_val = 0.0
teil_counter[teil_str] += 1
rows_data.append((pos_str, teil_str, bez_str, menge_val))
unique_teile = {t for t, count in teil_counter.items() if count == 1}
# Second pass: build tree with Teilenummer-based keys
tree: dict = {}
pos_to_node: dict[str, dict] = {} # maps position path -> dict node
# Track metadata per node for leaf post-processing
node_meta: dict[int, tuple[str, str, float]] = {} # id(child) -> (teil_str, bez_str, menge)
for pos_str, teil_str, bez_str, menge_val in rows_data:
key = make_key(teil_str, bez_str, teil_str in unique_teile)
segments = pos_str.split("/")
# Find parent dict
if len(segments) == 1:
parent = tree
else:
parent_pos = "/".join(segments[:-1])
if parent_pos not in pos_to_node:
# Parent row missing in data, create placeholder
pos_to_node[parent_pos] = {}
parent = pos_to_node[parent_pos]
# Insert with unique key
final_key = unique_key(parent, key)
child: dict = {}
parent[final_key] = child
pos_to_node[pos_str] = child
node_meta[id(child)] = (teil_str, bez_str, menge_val)
is_sivas = re.compile(r"^\d{9}$").match
# Post-process: leaves (empty dicts) -> key=Teilenummer, value=Bezeichnung
def simplify_leaves(node: dict) -> dict:
result: dict = {}
for key, value in node.items():
if isinstance(value, dict) and len(value) == 0:
# Leaf node: use only Teilenummer as key, Bezeichnung as value
teil, bez, menge = node_meta.get(id(value), ("", "", 0.0))
if teil in LAENGENABHAENGIG:
# Length-dependent part: sum up Menge as laenge
if teil in result and isinstance(result[teil], dict) and "laenge" in result[teil]:
result[teil]["laenge"] += menge
elif teil in result and isinstance(result[teil], str):
result[teil] = {"laenge": menge, "beschreibung": result[teil]}
else:
leaf_key = unique_key(result, teil)
result[leaf_key] = {"laenge": menge, "beschreibung": bez}
elif teil in result and is_sivas(teil):
# Aggregate duplicate 9-digit Sivas numbers
existing = result[teil]
if isinstance(existing, str):
result[teil] = {"anzahl": 2, "beschreibung": existing}
else:
existing["anzahl"] += 1
else:
leaf_key = unique_key(result, teil)
result[leaf_key] = bez
elif isinstance(value, dict):
# Branch node: enrich bare 9-digit keys with Bezeichnung
branch_key = key
if is_sivas(key):
teil, bez, _ = node_meta.get(id(value), ("", "", 0.0))
if bez:
branch_key = f"{teil}-{bez}".replace(" ", "_")
branch_key = unique_key(result, branch_key)
else:
branch_key = unique_key(result, key)
result[branch_key] = simplify_leaves(value)
else:
result[key] = value
return result
return simplify_leaves(tree)
def process_file(xlsx_path: Path, sheet_name: str, tab: str, results_dir: Path,
out_path: Path | None = None) -> bool:
"""Process a single xlsx file. Returns True on success."""
print(f"Lade: {xlsx_path.name}")
print(f"Sheet: {sheet_name}")
wb = openpyxl.load_workbook(str(xlsx_path), data_only=True)
# Find matching sheet: try exact (case-insensitive), then pattern matching
actual_name = None
for name in wb.sheetnames:
if name.lower() == sheet_name.lower():
actual_name = name
break
if actual_name is None:
for pattern in SHEET_PATTERNS.get(tab, []):
for name in wb.sheetnames:
if pattern.search(name):
actual_name = name
break
if actual_name:
break
if actual_name is None:
print(f" SKIP: Kein passendes Sheet fuer '{tab}' gefunden. Vorhanden: {wb.sheetnames}")
return False
ws = wb[actual_name]
tree = build_tree(ws, tab)
if out_path is None:
stem = xlsx_path.stem.replace(" ", "_")
out_path = results_dir / f"{stem}_{tab}.json"
with open(out_path, "w", encoding="utf-8") as f:
json.dump(tree, f, indent=2, ensure_ascii=False)
print(f" Ausgabe: {out_path}")
return True
def main():
parser = argparse.ArgumentParser(
description="Erzeugt eine JSON-Baumstruktur aus der Positionsspalte einer Excel-Stueckliste."
)
parser.add_argument(
"--filename",
default=None,
help="Suchmuster fuer die .xlsx-Datei im examples/-Ordner (z.B. 'Fortna')",
)
parser.add_argument(
"--tab",
choices=["soll", "ist"],
default="soll",
help="Welches Tabellenblatt gelesen wird: 'soll' oder 'ist' (default: soll)",
)
parser.add_argument(
"--output",
default=None,
help="Ausgabedatei (default: <filename>_<tab>.json im results/-Ordner)",
)
parser.add_argument(
"--all",
action="store_true",
dest="process_all",
help="Alle .xlsx-Dateien im examples/-Ordner in _ist und _soll JSON konvertieren",
)
args = parser.parse_args()
if not args.process_all and not args.filename:
parser.error("Entweder --filename oder --all muss angegeben werden.")
# Resolve paths relative to project root
project_root = Path(os.environ.get("PROJECT", Path(__file__).resolve().parent.parent))
examples_dir = project_root / "examples"
results_dir = project_root / "results"
results_dir.mkdir(exist_ok=True)
tab = args.tab
if args.process_all:
xlsx_files = sorted(f for f in Path(examples_dir).glob("*.xlsx")
if not f.name.startswith("~$"))
print(f"Verarbeite {len(xlsx_files)} Dateien aus {examples_dir}\n")
ok, skip = 0, 0
tabs = [tab] if tab != "soll" or "--tab" in sys.argv else ["soll", "ist"]
for xlsx_path in xlsx_files:
for t in tabs:
sheet_name = SHEET_NAMES[t]
if process_file(xlsx_path, sheet_name, t, results_dir):
ok += 1
else:
skip += 1
print()
print(f"Fertig: {ok} JSON erzeugt, {skip} uebersprungen.")
else:
xlsx_path = find_xlsx(str(examples_dir), args.filename)
sheet_name = SHEET_NAMES[tab]
out_path = None
if args.output:
out_path = Path(args.output)
if not out_path.is_absolute():
out_path = results_dir / out_path
if not process_file(xlsx_path, sheet_name, tab, results_dir, out_path):
sys.exit(1)
if __name__ == "__main__":
main()