adds urn check digit result to JSON

ceurws/__init__.py

@@ -1 +1 @@
-__version__ = "0.3.2"
+__version__ = "0.3.3"

ceurws/urn.py

@@ -0,0 +1,71 @@
+"""
+Created on 2023-12-28
+
+@author: wf / ChatGPT-4 as instructed
+"""
+
+
+class URN:
+    """
+    URN check digit calculator for DNB URN service:
+
+    see https://www.dnb.de/DE/Professionell/Services/URN-Service/urn-service_node.html
+
+    and
+        https://d-nb.info/1045320641/34
+        http://nbn-resolving.de/nbnpruefziffer.php
+
+    """
+
+    @classmethod
+    def check_urn_checksum(cls, urn: str, debug: bool = False) -> bool:
+        expected_check_digit = int(urn[-1])
+        urn_prefix = urn[:-1]
+        check_digit = cls.calc_urn_checksum(urn_prefix, debug)
+        return check_digit == expected_check_digit
+
+    @classmethod
+    def calc_urn_checksum(cls, test_urn: str, debug: bool = False) -> int:
+        """
+        converted from PHP and JavaScript code see
+        see https://github.com/bohnelang/URN-Pruefziffer
+
+        Args:
+            debug(bool) if True show the internal values while calculating
+        """
+        # Code string provided in the original PHP function
+        code = "3947450102030405060708094117############1814191516212223242542262713282931123233113435363738########43"
+
+        # Initialization of variables
+        _sum = 0
+        pos = 1
+
+        # Iterating through each character in the URN
+        for i, char in enumerate(test_urn.upper()):
+            # Getting the ASCII value and adjusting it based on the character '-' (45 in ASCII)
+            x = ord(char) - 45
+            # Extracting two consecutive values from the code string
+            v1 = int(code[x * 2]) if code[x * 2] != "#" else 0
+            v2 = int(code[x * 2 + 1]) if code[x * 2 + 1] != "#" else 0
+
+            if v1 == 0:
+                # If v1 is 0, increment pos after multiplying v2 with its current value
+                _sum += v2 * pos
+                pos += 1  # post-increment equivalent in Python
+            else:
+                # If v1 is not 0, use pos for the first term, increment pos, then use the new value of pos for the second term
+                # This effectively increases pos by 2 in this branch
+                _sum += pos * v1
+                pos += 1  # increment for the first term
+                _sum += v2 * pos  # use incremented pos for the second term
+                pos += 1  # increment for the second term
+
+            if debug:
+                print(
+                    f"i: {i:2} pos: {pos:2} x: {x:2} v1: {v1:2} v2: {v2:2} sum: {_sum:4}"
+                )
+
+        # Assuming v2 is not 0 at the end of your URN calculations
+        check_digit = (_sum // v2) % 10  # Using integer division for floor behavior
+
+        return check_digit

ceurws/volumeparser.py

@@ -12,7 +12,7 @@
 
 from ceurws.textparser import Textparser
 from ceurws.utils.webscrape import ScrapeDescription, WebScrape
-
+from ceurws.urn import URN
 
 class VolumeParser(Textparser):
     """
@@ -125,8 +125,21 @@ def parse_volume(
         """
         soup = self.get_volume_soup(number, use_cache=use_cache)
         parsed_dict = self.parse_soup(number, soup)
+        self.check_parsed_dict(parsed_dict)
         return parsed_dict, soup
-
+
+    def check_parsed_dict(self,parsed_dict:dict):
+        """
+        check parsed_dict content e.g. urn check digit
+        """
+        if "urn" in parsed_dict:
+            urn=parsed_dict["urn"]
+            urn_prefix = urn[:-1]
+            check_digit=URN.calc_urn_checksum(urn_prefix)
+            parsed_dict["urn_check_digit"]=check_digit
+            urn_ok=URN.check_urn_checksum(urn)
+            parsed_dict["urn_ok"]=urn_ok
+
     def parse(self, url: str) -> dict:
         """
         parse the given url

tests/test_urn.py

@@ -0,0 +1,51 @@
+"""
+Created on 2023-12-28
+
+@author: wf
+"""
+from ceurws.urn import URN
+from tests.basetest import Basetest
+
+
+class TestURN(Basetest):
+    """
+    Test URN checkdigit calculation
+    """
+
+    def test_urn_check_digits(self):
+        """
+        test some examples
+        """
+        debug = self.debug
+        verbose = False
+        urns = [
+            "urn:nbn:de:0183-mbi0003721",
+            "urn:nbn:de:0074-1000-9",
+            "urn:nbn:de:0074-1001-3",
+            "urn:nbn:de:0074-1002-6",
+            "urn:nbn:de:0074-1003-0",
+            "urn:nbn:de:0074-1004-3",
+            "urn:nbn:de:0074-1005-7",
+            "urn:nbn:de:0074-1006-1",
+            "urn:nbn:de:0074-1007-4",
+            "urn:nbn:de:0074-1008-8",
+            "urn:nbn:de:0074-1009-5",
+            "urn:nbn:de:0074-1010-3",
+            "urn:nbn:de:0074-1011-6",
+            "urn:nbn:de:0074-1012-0",
+            "urn:nbn:de:0074-1013-3",
+            "urn:nbn:de:0074-1014-7",
+            "urn:nbn:de:0074-1015-0",
+            "urn:nbn:de:0074-1016-4",
+            "urn:nbn:de:0074-1017-8",
+        ]
+        for i, urn in enumerate(urns, start=1):
+            urn_prefix = urn[:-1]
+            expected = urn[-1]
+            digit = URN.calc_urn_checksum(urn_prefix)
+            if verbose:
+                check_mark = "✅" if expected == str(digit) else "❌"
+                print(f"{i:2} {check_mark}:{digit}:{urn_prefix}:{urn}")
+
+        for urn in urns:
+            self.assertTrue(URN.check_urn_checksum(urn, debug))

tests/test_volumeparser.py

@@ -53,7 +53,8 @@ def testVolumeParser(self):
                 volnumber, use_cache=True
             )
             if debug:
-                print(f"Vol-{volnumber}:{scrapedDict}")
+                scraped_str=json.dumps(scrapedDict,indent=2)
+                print(f"Vol-{volnumber}:{scraped_str}")
 
     def testIssue41(self):
         """