#11: Ontologia.est_validum_ad_regula(); cor.hxltm.215.yml:ontologia_r…

…egulam

.github/workflows/hxltm-computo_testum.yml

@@ -23,7 +23,7 @@ jobs:
     strategy:
       matrix:
         # python-version: [3.7, 3.8, 3.9, 3.10]
-        python-version: [3.7, 3.8, 3.9]
+        python-version: [3.7, 3.8, 3.9, 3.10]
 
     # # Don't run https://github.com/nektos/act locally. Can be removed later. 
     # if: ${{ !env.ACT }}

bin/hxltmcli.py

@@ -5026,10 +5026,9 @@ class HXLTMOntologia:
 >>> ontologia.quid_est_hashtag_circa_linguam('#item+conceptum+codicem')
 False
 
->>> ontologia.quid_est_hashtag_circa_linguam('#rem+rem+i_la+i_lat+is_latn')
+>>> ontologia.est_validum_ad_regula('#item+conceptum+codicem')
 True
 
-
 #>>> ontologia.quod_rem_statum()
 {'accuratum': None, 'crudum': [], 'crudum_originale': [], \
 'XLIFF': 'initial', 'UTX': 'provisional'}
@@ -5061,6 +5060,16 @@ def __init__(self, ontologia: Dict, vacuum: bool = False):
         else:
             self.crudum = ontologia
 
+    def _ontologia_regulam_regex(self, clavem: str) -> str:
+        """_ontologia_regulam_regex
+        """
+        try:
+            return self.crudum['ontologia_regulam'][clavem]
+            # return self.crudum['ontologia_regulam'][clavem]['regex']
+        except:
+            raise ValueError(
+                'Non {0} ad ontologia_regulam.{0}.regex'.format(clavem))
+
     def hxl_de_aliud_nomen_breve(self, structum=False):
         """HXL attribūtum de aliud nōmen breve (cor.hxltm.215.yml)
 
@@ -5157,6 +5166,36 @@ def de(self, dotted_key: str,  # pylint: disable=invalid-name
                 key) if d else default, keys, fontem
         )
 
+    def est_validum_ad_regula(
+            self,
+            hxlhashtag: str,
+            regulam_clavem: str = None
+    ) -> bool:
+        """est_validum_ad_regula est validum ad rēgulam? [ ontologia_regulam ]
+
+        _[eng-Latn]
+        Is this hashtag valid based on Ontologia regexes?
+        [eng-Latn]_
+
+        Trivia:
+        - rēgulam, https://en.wiktionary.org/wiki/regula#Latin
+        - validum, https://en.wiktionary.org/wiki/validus#Latin
+
+        Args:
+            hxlhashtag (str): HXL Hashtag
+            ontologia_regex (str, optional): ontologia_regulam clavem
+
+        Returns:
+            bool: Python True est validum
+        """
+        if regulam_clavem is None:
+            regulam_clavem = 'abstractum_aut_concretum'
+
+        regula = self._ontologia_regulam_regex(regulam_clavem)
+        regula_regex = re.compile(regula['regex'])
+
+        return bool(regula_regex.match(hxlhashtag))
+
     def quod_aliud(self, aliud_typum: str, aliud_valorem: str) -> Dict:
         """Quod Aliud?
 
@@ -5418,9 +5457,38 @@ def quod_rem_statum(self,
         # TODO: implement this check
         return resultatum
 
-    @staticmethod
+    # @staticmethod
+    # def quid_est_columnam_aut_lineam(
+    #         hxl_hashtag: str) -> Union[str, None]:
+    #     """Quid est columnam aut līneam?
+
+    #     _[eng-Latn]
+    #     Is this hashtag type maximixed columns or maximized rows?
+    #     See https://en.wikipedia.org/wiki/Wide_and_narrow_data
+    #     [eng-Latn]
+
+    #     Args:
+    #         hxl_hashtag (str): Hashtag ad textum
+
+    #     Returns:
+    #         str: 'columnam', 'lineam', None
+    #     """
+    #     # TODO: make this actually read the cor.hxltm.215.yml. This hardcoded
+    #     #       part is just a quick fix
+
+    #     if HXLTMOntologia.quid_est_hashtag_circa_conceptum(hxl_hashtag):
+    #         # Concept hashtags are neither cases
+    #         return None
+
+    #     if hxl_hashtag.find('+conceptum') > -1:
+    #         return True
+
+    #     return False
+
     def quid_est_hashtag_circa_conceptum(
-            hxl_hashtag: str) -> Union[bool, None]:
+        self,
+        hxl_hashtag: str
+    ) -> Union[bool, None]:
         """Quid est hashtag circa +conceptum?
 
         _[eng-Latn]
@@ -5436,16 +5504,15 @@ def quid_est_hashtag_circa_conceptum(
         # TODO: make this actually read the cor.hxltm.215.yml. This hardcoded
         #       part is just a quick fix
 
-        if HXLTMOntologia.quid_est_hashtag_circa_linguam(hxl_hashtag):
+        if self.quid_est_hashtag_circa_linguam(hxl_hashtag):
             return False
 
         if hxl_hashtag.find('+conceptum') > -1:
             return True
 
         return False
 
-    @staticmethod
-    def quid_est_hashtag_circa_linguam(hxl_hashtag: str) -> bool:
+    def quid_est_hashtag_circa_linguam(self, hxl_hashtag: str) -> bool:
         """Quid est hashtag circa linguam?
 
         _[eng-Latn]
@@ -5462,9 +5529,13 @@ def quid_est_hashtag_circa_linguam(hxl_hashtag: str) -> bool:
         #       part is just a quick fix
 
         if hxl_hashtag.startswith('#item+rem+i_'):
+            self._deprecatum.add('deprecatum [{0}]'.format(hxl_hashtag))
             return True
+
         if hxl_hashtag.startswith('#meta+rem+i_'):
+            self._deprecatum.add('deprecatum [{0}]'.format(hxl_hashtag))
             return True
+
         if re.match(r"\#.*(\+i_).*(\+is_).*", hxl_hashtag):
             # # +i_ +is_
             return True
@@ -7836,7 +7907,7 @@ def __enter__(self):
     def __exit__(self, value, type, traceback):
         pass
 
-    def write(self, s): # pylint: disable=invalid-name
+    def write(self, s):  # pylint: disable=invalid-name
         self.output.write(s)
 
 

ontologia/cor.hxltm.215.yml

@@ -2995,6 +2995,27 @@ ontologia_aliud_familiam:
 
 # end::ontologia_aliud[]
 
+
+# Trivia: rēgulam, https://en.wiktionary.org/wiki/regula#Latin
+ontologia_regulam:
+  # @see https://regex101.com/ (online regex tester, multiple engines)
+  # @see https://docs.python.org/3/howto/regex.html
+  # @see https://developer.mozilla.org/en-US/docs/Web/JavaScript
+  #      /Reference/Global_Objects/RegExp
+  # @see https://pkg.go.dev/regexp/syntax
+  # @see https://www.php.net/manual/en/reference.pcre.pattern.syntax.php
+
+  # abstractum, https://en.wiktionary.org/wiki/abstractus#Latin
+  abstractum:
+    regex: "^#item"
+
+  abstractum_aut_concretum:
+    regex: "^#item|^#meta"
+
+  # concrētum, https://en.wiktionary.org/wiki/concretus
+  concretum:
+    regex: "^#item"
+
 ## TBX Basic 3.1 (http://www.terminorgs.net/downloads/TBX_Basic_Version_3.1.pdf)
 #  5 Mandatory data categories
 #  There are only two mandatory data categories in TBX-Basic: term, and language.

testum/hxltmcli--help_eng-Latn.txt

@@ -18,6 +18,8 @@ usage: hxltmcli [-h] [--sheet [number]] [--selector [path]]
                 [--objectivum-CSV-3] [--objectivum-TSV-3]
                 [--objectivum-JSON-kv]
                 [--objectivum-formatum-speciale [objectivum_formatum_speciale]]
+                [--transformare-ad-maximum-columnam]
+                [--transformare-ad-maximum-lineam]
                 [--limitem-quantitatem [limitem_quantitatem]]
                 [--limitem-initiale-lineam [limitem_initiale_lineam]]
                 [--non-securum-limitem]
@@ -156,6 +158,20 @@ optional arguments:
                         Example: "hxltmcli fontem.hxl.csv objectivum.tmx
                         --objectivum-TMX --objectivum-formatum-speciale TMX-
                         de-marcus"
+  --transformare-ad-maximum-columnam
+                        (Early draft) Transformation of type reshape entire
+                        dataset. Convert HXLTM narrow (more rows) to wide
+                        (more columns; each new language means add more
+                        columns). more columns; also called vertical database
+                        model or open schema). See
+                        https://en.wikipedia.org/wiki/Wide_and_narrow_data.
+  --transformare-ad-maximum-lineam
+                        (Early draft) Transformation of type reshape entire
+                        dataset. Convert HXLTM wide (more columns; each new
+                        language means add more columns) to narrow (more rows;
+                        each new language does not require more columns; also
+                        called vertical database model or open schema). See
+                        https://en.wikipedia.org/wiki/Wide_and_narrow_data.
   --limitem-quantitatem [limitem_quantitatem]
                         (Advanced, large data sets) Customize the limit of the
                         maximum number of raw rows can be in a single step.