120 lines
6.8 KiB
Python
120 lines
6.8 KiB
Python
"""Extract only this workbook's local detail cells; never evaluate external links."""
|
||
|
||
import hashlib
|
||
from pathlib import Path
|
||
import posixpath
|
||
import re
|
||
from xml.etree import ElementTree as ET
|
||
from zipfile import ZipFile
|
||
|
||
from .quote_data import decimal_text
|
||
|
||
|
||
NS = {'s':'http://schemas.openxmlformats.org/spreadsheetml/2006/main'}
|
||
TRUCK_SHEETS = ('美森正班海卡','美森加班海卡','EXX海卡','合德海卡','纽约EXX海铁',
|
||
'洛杉矶普船海卡','洛杉矶普船全卡','芝加哥普船海铁','休斯顿普船海卡','纽约普船海卡','萨凡纳普船海卡')
|
||
|
||
|
||
def read_sheets(path):
|
||
path = Path(path)
|
||
if path.stat().st_size > 20*1024*1024:
|
||
raise ValueError('Quote workbook is too large')
|
||
with ZipFile(path) as archive:
|
||
if sum(info.file_size for info in archive.infolist()) > 100*1024*1024:
|
||
raise ValueError('Expanded quote workbook is too large')
|
||
strings = []
|
||
if 'xl/sharedStrings.xml' in archive.namelist():
|
||
for entry in ET.fromstring(archive.read('xl/sharedStrings.xml')):
|
||
strings.append(''.join(t.text or '' for t in entry.findall('.//s:t', NS)))
|
||
workbook = ET.fromstring(archive.read('xl/workbook.xml'))
|
||
rels = {r.attrib['Id']:r.attrib['Target'] for r in ET.fromstring(archive.read('xl/_rels/workbook.xml.rels'))}
|
||
result = {}
|
||
for sheet in workbook.find('s:sheets', NS):
|
||
target = rels[sheet.attrib['{http://schemas.openxmlformats.org/officeDocument/2006/relationships}id']]
|
||
target = target.lstrip('/') if target.startswith('/') else posixpath.normpath('xl/'+target)
|
||
rows = {}
|
||
for cell in ET.fromstring(archive.read(target)).findall('s:sheetData/s:row/s:c', NS):
|
||
ref = cell.attrib['r']
|
||
column = re.sub('[0-9]', '', ref)
|
||
if len(column) != 1 or column > 'Q':
|
||
continue
|
||
raw = cell.find('s:v', NS)
|
||
value = raw.text if raw is not None else ''
|
||
if cell.attrib.get('t') == 's':
|
||
value = strings[int(value)]
|
||
elif cell.attrib.get('t') == 'inlineStr':
|
||
value = ''.join(t.text or '' for t in cell.findall('.//s:t', NS))
|
||
formula = cell.find('s:f', NS)
|
||
if formula is not None and formula.text and re.search(r'\[[0-9]+\]', formula.text):
|
||
continue
|
||
if value:
|
||
rows.setdefault(int(re.sub('[^0-9]', '', ref)), {})[column] = value
|
||
result[sheet.attrib['name']] = rows
|
||
return result
|
||
|
||
|
||
def export_snapshot(path):
|
||
sheets = read_sheets(path)
|
||
missing = set(TRUCK_SHEETS + ('海派','FBA分区表','亚马逊仓库代码表','UPS&FedEx偏远地区表')) - sheets.keys()
|
||
if missing:
|
||
raise ValueError('Quote workbook is missing required local detail sheets')
|
||
result = {'schema':1, 'source_name':Path(path).name,
|
||
'source_sha256':hashlib.sha256(Path(path).read_bytes()).hexdigest(),
|
||
'rates':[], 'warehouses':[], 'postcodes':[], 'documents':[]}
|
||
for name in TRUCK_SHEETS:
|
||
rows = sheets[name]
|
||
destination_col = 'A' if name in TRUCK_SHEETS[:4] else 'B'
|
||
price_cols = ('B','C','D') if destination_col == 'A' else ('C','D','E')
|
||
eta_col = 'E' if destination_col == 'A' else 'F'
|
||
for number, row in rows.items():
|
||
if number < 6 or not re.fullmatch(r'\d+(?:\.\d+)?', row.get(price_cols[0], '')):
|
||
continue
|
||
destinations = [p.strip() for p in re.split(r'[/\n、]+', row.get(destination_col, '')) if p.strip()]
|
||
if not destinations:
|
||
raise ValueError('Price row is missing destinations')
|
||
for column, origin, unit, tax in zip(price_cols, ('义乌','义乌','华南'), ('cbm','kg','kg'), ('excluded','included','included')):
|
||
result['rates'].append({'service':name, 'kind':'truck', 'origin':origin, 'zone':'',
|
||
'unit':unit, 'tax':tax, 'min_weight':'0', 'price':decimal_text(row[column], positive=True),
|
||
'eta':row.get(eta_col, ''), 'destinations':destinations, 'source_sheet':name, 'source_cell':f'{column}{number}'})
|
||
parcel = sheets['海派']
|
||
for origin, header, first in (('义乌',4,9), ('华南',13,18)):
|
||
for start_col in ('C','F','I','L'):
|
||
for offset, tier in enumerate(('12','51','101')):
|
||
column = chr(ord(start_col)+offset)
|
||
for index, zone in enumerate(('美西','美中','美东')):
|
||
number = first+index
|
||
result['rates'].append({'service':parcel[header][start_col], 'kind':'parcel', 'origin':origin,
|
||
'zone':zone, 'unit':'kg', 'tax':'included', 'min_weight':tier,
|
||
'price':decimal_text(parcel[number][column], positive=True),
|
||
'eta':parcel[header+2][start_col], 'destinations':[], 'source_sheet':'海派', 'source_cell':f'{column}{number}'})
|
||
for name, first in (('FBA分区表',3), ('亚马逊仓库代码表',2)):
|
||
for number, row in sheets[name].items():
|
||
if number < first or not row.get('A'):
|
||
continue
|
||
is_zone = name == 'FBA分区表'
|
||
result['warehouses'].append({'code':row['A'].strip().upper(),
|
||
'zone':row.get('B','') if is_zone else '', 'state':row.get('C','') if is_zone else '',
|
||
'postal':row.get('D','') if is_zone else '', 'address':row.get('B','') if not is_zone else '',
|
||
'source_sheet':name, 'source_cell':f'A{number}'})
|
||
for number, row in sheets['UPS&FedEx偏远地区表'].items():
|
||
if number <= 23:
|
||
continue
|
||
for column, severity, fee in (('B','remote','1'), ('F','extended','2'), ('J','extreme',None)):
|
||
postal = row.get(column, '')
|
||
if postal:
|
||
result['postcodes'].append({'postal':postal, 'severity':severity, 'fee':fee})
|
||
for name, rows in sheets.items():
|
||
if name in ('快速查询','UPS&FedEx偏远地区表','FBA分区表','亚马逊仓库代码表'):
|
||
continue
|
||
for number, row in rows.items():
|
||
if number <= 1 or (name in TRUCK_SHEETS and number <= 5):
|
||
continue
|
||
# Long detail text contains rules; short lookup rows contain service fees.
|
||
for column, value in row.items():
|
||
if len(value) >= 20 and not re.search(r'公司地址|TEL:|船名航次|预计开船日期|关税查询网址', value):
|
||
result['documents'].append({'sheet':name, 'cell':f'{column}{number}', 'text':value})
|
||
if name in ('一件代发收费','FDA申报清单'):
|
||
text = '；'.join(row.values())
|
||
result['documents'].append({'sheet':name,'cell':f'A{number}','text':text})
|
||
return result
|