三分一技術士事務所

.
├── common
│   └── docs
│       ├── bis.pdf
│       ├── compliance.pdf
│       └── release-notes.pdf
└── trn-invoice
    ├── codelist
    │   ├── Aligned-TaxCategoryCodes.gc
    │   ├── Aligned-TaxCategoryCodes.yaml
    │   ├── Aligned-TaxExemptionCodes.gc
    │   ├── Aligned-TaxExemptionCodes.yaml
    │   ├── ICD.gc
    │   ├── ICD.yaml
    │   ├── ISO3166.gc
    │   ├── ISO3166.yaml
    │   ├── ISO4217.gc
    │   ├── ISO4217.yaml
    │   ├── MimeCode.gc
    │   ├── MimeCode.yaml
    │   ├── SEPA.gc
    │   ├── SEPA.yaml
    │   ├── UNCL1001-inv.gc
    │   ├── UNCL1001-inv.yaml
    │   ├── UNCL1153.gc
    │   ├── UNCL1153.yaml
    │   ├── UNCL2005.gc
    │   ├── UNCL2005.yaml
    │   ├── UNCL4461.gc
    │   ├── UNCL4461.yaml
    │   ├── UNCL5189.gc
    │   ├── UNCL5189.yaml
    │   ├── UNCL7143.gc
    │   ├── UNCL7143.yaml
    │   ├── UNCL7161.gc
    │   ├── UNCL7161.yaml
    │   ├── UNECERec20.gc
    │   ├── UNECERec20.yaml
    │   ├── eas.gc
    │   └── eas.yaml
    ├── schematron
    │   ├── PINT-UBL-validation-preprocessed.sch
    │   └── PINT-jurisdiction-aligned-rules.sch
    ├── semantic-model.yaml
    └── syntax-binding.yaml

  
    Aligned tax category codes
    D.16B
  
  
    
      Identifier
      
    
    
      Name
      
    
    
      Description
      
    
    
      
    
  
  
    
      
        AA
      
      
        Lower rate
      
      
        Tax rate is lower than standard rate.
      
    
    
      
        E
      
      
        Exempt from tax
      
      
        Code specifying that taxes are not applicable.
      
    
    
      
        G
      
      
        Free export item, tax not charged
      
      
        Code specifying that the item is free export and taxes are not charged.
      
    
    
      
        O
      
      
        Outside scope of tax
      
      
        Code specifying not subject to tax.
      
    
    
      
        S
      
      
        Standard rate
      
      
        Code specifying the standard rate.
      
    
  

metadata:
  title:
    en: Aligned tax category codes
  description:
    en: Codes specifying tax categories in jurisdictions.
  identifier: AlignedTaxCat
  agency: UN/CEFACT
  language: en
  version:
    identifier: D.16B
    status: published
content:
- id: AA
  name:
    en: Lower rate
  description:
    en: Tax rate is lower than standard rate.
- id: E
  name:
    en: Exempt from tax
  description:
    en: Code specifying that taxes are not applicable.
- id: G
  name:
    en: Free export item, tax not charged
  description:
    en: Code specifying that the item is free export and taxes are not charged.
- id: O
  name:
    en: Outside scope of tax
  description:
    en: Code specifying not subject to tax.
- id: S
  name:
    en: Standard rate
  description:
    en: Code specifying the standard rate.

.
└── trn-invoice
    ├── schematron
    │   ├── PINT-UBL-validation-preprocessed.sch
    │   └── PINT-jurisdiction-aligned-rules.sch

#!/usr/bin/env python3
#coding: utf-8
#
# generate JSON from XML Schematron
#
# designed by SAMBUICHI, Nobuyuki (Sambuichi Professional Engineers Office)
# written by SAMBUICHI, Nobuyuki (Sambuichi Professional Engineers Office)
#
# MIT License
#
# Copyright (c) 2021 SAMBUICHI Nobuyuki (Sambuichi Professional Engineers Office)
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
import xml.etree.ElementTree as ET
from collections import defaultdict
import re
import json
import sys
import os
import argparse

from dic2etree import *

dictID = defaultdict(type(''))
dictXpath = defaultdict(type(''))

def file_path(pathname):
  if '/' == pathname[0:1]:
    return pathname
  else:
    dir = os.path.dirname(__file__)
    new_path = os.path.join(dir, pathname)
    return new_path

def dict_to_tsv(tsv, root):
  def setup_record(context, id, flag, test, text):
    test = test.strip()
    test = ' '.join(test.split())
    text = text.strip()
    text = ' '.join(text.split())
    terms_pattern = 'I?BT-[0-9]*'
    terms = re.findall(terms_pattern, text, flags=re.IGNORECASE)
    terms = ' '.join(terms)
    groups_pattern = 'I?BG-[0-9]*'
    groups = re.findall(groups_pattern, text, flags=re.IGNORECASE)
    groups = ' '.join(groups)
    record = [context, id, flag, test, text, groups, terms]
    return record

  def process_pattern(tsv, pattern):
    pattern_id = pattern['@id']
    rules = pattern['sch:rule']
    if isinstance(rules, dict):
      try:
        context = rules['@context']
        d = rules['sch:assert']
        if isinstance(d, list):
          for v in d:
            record = setup_record(context, v['@id'], v['@flag'], v['@test'], v['#text'])
            tsv.append(record)
        elif isinstance(d, dict):
          record = setup_record(context, d['@id'], d['@flag'], d['@test'], d['#text'])
          tsv.append(record)
        else:
          if verbose:
            print(json.dumps(d))
          pass
      except Exception as expt:
        if verbose:
          print(expt.args)
        pass
    elif isinstance(rules, list):
      for rule in rules:
        try:
          context = rule['@context']
          d = rule['sch:assert']
          if isinstance(d, list):
            for v in d:
              record = setup_record(context, v['@id'], v['@flag'], v['@test'], v['#text'])
              tsv.append(record)
          elif isinstance(d, dict):
            record = setup_record(context, d['@id'], d['@flag'], d['@test'], d['#text'])
            tsv.append(record)
          else:
            if verbose:
              print(json.dumps(d))
            pass
        except Exception as expt:
          if verbose:
            print(expt.args)
          pass
    else:
      pass
    return tsv

  tsv.append(record)
  if 'sch:pattern' in root:
    pattern = root['sch:pattern']
    tsv = process_pattern(tsv, pattern)
  elif root['sch:schema'] and isinstance(root['sch:schema'], dict):
    for tag, body in root['sch:schema'].items():
      if 'sch:pattern' == tag:
        for pattern in body:
          tsv = process_pattern(tsv, pattern)

if __name__ == '__main__':
  # Create the parser
  parser = argparse.ArgumentParser(prog='invoice2tsv',
                                  usage='%(prog)s [options] pintFile -o out_file',
                                  description='スキーマトロンファイルをjsonファイルに変換')
  # Add the arguments
  parser.add_argument('pintFile', metavar='pintfile', type=str, help='入力スキーマトロンファイル)
  parser.add_argument('-o', '--out')
  parser.add_argument('-v', '--verbose', action='store_true')
  args = parser.parse_args()
  pint_file = file_path(args.pintFile)
  pre, ext = os.path.splitext(pint_file)
  # tmp_file = pre + '.tmp'
  if args.out:
    out_file = args.out.lstrip()
    out_file = file_path(out_file)
  else:
    out_file = pre + '.json'
  verbose = args.verbose
  # Check if infile exists
  if not os.path.isfile(pint_file):
    print('入力ファイルがありません')
    sys.exit()
  if verbose:
    print('** START ** ', __file__)

  pint_tree = ET.parse(pint_file)
  pint_root = pint_tree.getroot()

  pint_dict = etree_to_dict(pint_root)

  dicJson = json.dumps(pint_dict)
  dicJson = re.sub('{' + ns[''] + '}', '', dicJson)
  dicJson = re.sub('{' + ns['cac'] + '}', 'cac:', dicJson)
  dicJson = re.sub('{' + ns['cbc'] + '}', 'cbc:', dicJson)
  dicJson = re.sub('{' + ns['sch'] + '}', 'sch:', dicJson)
  pint_dict2 = json.loads(dicJson)
  pint_tsv = []
  dict_to_tsv(pint_tsv, pint_dict2)

  pint_set = set([json.dumps(x) for x in pint_tsv])
  pint_list = list(pint_set)
  tsv = [json.loads(w) for w in pint_list]
  header = ['Context', 'Identifier', 'Flag', 'Test', 'Message', 'BG', 'BT']
  rules = []
  for d in tsv:
    rule = {}
    i = 0
    for h in header:
      rule[h] = d[i]
      i += 1
    rules.append(rule)

  with open(out_file,'w',newline='') as f:
    json.dump(rules, f, indent=4)

  if verbose:
    print(f'** END ** {out_file}')

├── dic2etree
│   ├── __init__.py
│   └── dic2etree.py

from .dic2etree import dict_to_etree
from .dic2etree import etree_to_dict
ns = {
  '': 'urn:oasis:names:specification:ubl:schema:xsd:Invoice-2',
  'xsd': 'http://www.w3.org/2001/XMLSchema',
  'xsi': 'http://www.w3.org/2001/XMLSchema-instance',
  'ext': 'urn:oasis:names:specification:ubl:schema:xsd:CommonExtensionComponents-2',
  'cac': 'urn:oasis:names:specification:ubl:schema:xsd:CommonAggregateComponents-2',
  'cbc': 'urn:oasis:names:specification:ubl:schema:xsd:CommonBasicComponents-2',
  'qdt': 'urn:oasis:names:specification:ubl:schema:xsd:QualifiedDataTypes-2',
  'udt': 'urn:oasis:names:specification:ubl:schema:xsd:UnqualifiedDataTypes-2',
  'ccts': 'urn:un:unece:uncefact:documentation:2',
  'cn': 'urn:oasis:names:specification:ubl:schema:xsd:CreditNote-2',
  'ubl': 'urn:oasis:names:specification:ubl:schema:xsd:Invoice-2',
  'sch': 'http://purl.oclc.org/dsdl/schematron'
}
__all__ = ['dict_to_etree', 'etree_to_dict', 'ns']

# convert between ElementTree from/to dict
#
# designed by SAMBUICHI, Nobuyuki (Sambuichi Professional Engineers Office)
# written by SAMBUICHI, Nobuyuki (Sambuichi Professional Engineers Office)
#
# MIT License
#
# Copyright (c) 2021 SAMBUICHI Nobuyuki (Sambuichi Professional Engineers Office)
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
import xml.etree.ElementTree as ET
from collections import defaultdict
import pprint

ET.register_namespace('cac', 'urn:oasis:names:specification:ubl:schema:xsd:CommonAggregateComponents-2')
ET.register_namespace('cbc', 'urn:oasis:names:specification:ubl:schema:xsd:CommonBasicComponents-2')
ET.register_namespace('qdt', 'urn:oasis:names:specification:ubl:schema:xsd:QualifiedDataTypes-2')
ET.register_namespace('udt', 'urn:oasis:names:specification:ubl:schema:xsd:UnqualifiedDataTypes-2')
ET.register_namespace('ccts', 'urn:un:unece:uncefact:documentation:2')
ET.register_namespace('', 'urn:oasis:names:specification:ubl:schema:xsd:Invoice-2')

# https://stackoverflow.com/questions/7684333/converting-xml-to-dictionary-using-elementtree
def etree_to_dict(t):
  d = {t.tag: {} if t.attrib else None}
  children = list(t)
  if children:
    dd = defaultdict(list)
    for dc in map(etree_to_dict, children):
      for k, v in dc.items():
        dd[k].append(v)
    d = {t.tag: {k: v[0] if len(v) == 1 else v for k, v in dd.items()}}
  if t.attrib:
    d[t.tag].update(('@' + k, v) for k, v in t.attrib.items())
  if t.text:
    text = t.text.strip()
    if children or t.attrib:
      if text:
        d[t.tag]['#text'] = text
    else:
      d[t.tag] = text
  return d

def dict_to_etree(d, root):
  def _to_etree(d, root):
    if not d:
      pass
    elif isinstance(d, str):
      root.text = d
    elif isinstance(d, dict):
      for k,v in d.items():
        assert isinstance(k, str)
        if k.startswith('#'):
          try:
            assert k == '#text' and isinstance(v, str)
            root.text = v
          except (Exception, ValueError, TypeError) as e:
            print(e, v)
        elif k.startswith('@'):
          if isinstance(v, str): # 2021-06-05
            root.set(k[1:], v)
          else:
            pass
        elif isinstance(v, list):
          for e in v:
            _to_etree(e, ET.SubElement(root, k))
        else:
          _to_etree(v, ET.SubElement(root, k))
    else:
      assert d == 'invalid type', (type(d), d)
  assert isinstance(d, dict) and len(d) == 1
  tag, body = next(iter(d.items()))
  _to_etree(body, root)
  return root