linkture 4.1.0__tar.gz → 4.2.0__tar.gz

{linkture-4.1.0 → linkture-4.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: linkture
-Version: 4.1.0
+Version: 4.2.0
 Summary: PARSE and PROCESS BIBLE SCRIPTURE REFERENCES: extract, tag, link, rewrite, translate, BCV-encode and decode
 Keywords: bible,scriptures,scripture-references,scripture-translation,scripture-parser,scripture-linker
 Author-Email: "Eryk J." <infiniti@inventati.org>
@@ -11,6 +11,7 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console
 Classifier: Topic :: Religion

{linkture-4.1.0 → linkture-4.2.0}/pyproject.toml

@@ -21,6 +21,7 @@ classifiers = [
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
     "Development Status :: 5 - Production/Stable",
     "Environment :: Console",
     "Topic :: Religion",
@@ -35,7 +36,7 @@ keywords = [
     "scripture-parser",
     "scripture-linker",
 ]
-version = "4.1.0"
+version = "4.2.0"
 
 [project.license]
 text = "MIT"

{linkture-4.1.0 → linkture-4.2.0}/src/linkture/linkture.py

@@ -27,7 +27,7 @@
 """
 
 __app__ = 'linkture'
-__version__ = 'v4.1.0'
+__version__ = 'v4.2.0'
 
 
 import json, regex, sqlite3
@@ -97,19 +97,16 @@ class Scriptures():
                     normalized = regex.sub(r'\p{P}|\p{Z}', '', item.upper())
                     self._src_book_names[normalized] = row[0]
 
-        # Ranges: {(book, chapter): last}  (chapter 0 -> num of chapters in book)
         self._ranges = {}
         for book, chapter, last in cur.execute("SELECT Book, Chapter, Last FROM Ranges;"):
             self._ranges[(book, chapter)] = last
 
-        # Chapters: two-way mappings
         self._chapters = {}
         self._chapters_id = {}
         for chapter_id, book, chapter in cur.execute("SELECT ChapterId, Book, Chapter FROM Chapters;"):
             self._chapters[(book, chapter)] = chapter_id
             self._chapters_id[chapter_id] = (book, chapter)
 
-        # Verses: two-way mappings
         self._verses = {}
         self._verses_id = {}
         for verse_id, book, chapter, verse in cur.execute("SELECT VerseId, Book, Chapter, Verse FROM Verses;"):
@@ -276,27 +273,29 @@ class Scriptures():
     def _code_scripture(self, scripture, bk_num, rest, last):
 
         def reform_series(txt): # rewrite comma-separated consecutive sequences (1, 2, 3) as ranges (1-3)
-            for result in self._d_dd.finditer(txt, overlapped=True):
-                    end = result.group(3)
-                    mid = result.group(2)
-                    start = result.group(1)
-                    if int(end) - int(mid) == 1:
-                        txt = regex.sub(result.group(), f"{start}-{end}", txt)
-            for result in self._ddd.finditer(txt, overlapped=True):
-                end = result.group(3)
-                start = result.group(1)
-                if int(end) - int(start) == 2:
-                    txt = regex.sub(result.group(), f"{start}-{end}", txt)
-            for result in self._ddd.finditer(txt, overlapped=True):
-                end = result.group(3)
-                start = result.group(1)
-                if int(end) - int(start) == 2:
-                    txt = regex.sub(result.group(), f"{start}-{end}", txt)
-            for result in self._dd.finditer(txt, overlapped=True):
-                    end = result.group(2)
-                    start = result.group(1)
-                    if int(end) - int(start) == 1:
-                        txt = regex.sub(result.group(), f"{start}-{end}", txt)
+            numbers = []
+            for match in regex.finditer(r'\d+', txt):
+                numbers.append((int(match.group()), match.start(), match.end()))
+            if not numbers:
+                return txt
+            sequences = []
+            current_seq = [numbers[0]]
+            for i in range(1, len(numbers)):
+                current_num = numbers[i][0]
+                prev_num = current_seq[-1][0]
+                if current_num == prev_num + 1:
+                    current_seq.append(numbers[i])
+                else:
+                    if len(current_seq) >= 3:
+                        sequences.append(current_seq)
+                    current_seq = [numbers[i]]
+            if len(current_seq) >= 3:
+                sequences.append(current_seq)
+            for seq in sorted(sequences, key=lambda x: x[0][1], reverse=True):
+                start_pos = seq[0][1]
+                end_pos = seq[-1][2]
+                replacement = f"{seq[0][0]}-{seq[-1][0]}"
+                txt = txt[:start_pos] + replacement + txt[end_pos:]
             return txt
 
         def validate(b, ch, vs):
@@ -435,6 +434,26 @@ class Scriptures():
 
             return None, None
 
+        def merge_ranges(ranges):
+            if not ranges:
+                return []
+            merged = []
+            current_start, current_end = ranges[0]
+            for start, end in ranges[1:]:
+                end_bk = int(current_end[:2])
+                end_ch = int(current_end[2:5])
+                end_vs = int(current_end[5:])
+                next_bk = int(start[:2])
+                next_ch = int(start[2:5])
+                next_vs = int(start[5:])
+                if (end_bk == next_bk and ((end_ch == next_ch and end_vs + 1 == next_vs) or (end_ch + 1 == next_ch and end_vs == self._ranges.get((end_bk, end_ch), 0) and next_vs == 1))):
+                    current_end = end
+                else:
+                    merged.append((current_start, current_end))
+                    current_start, current_end = start, end
+            merged.append((current_start, current_end))
+            return merged
+
         lst = []
         if rest == '': # whole book
             v = self._ranges.get((bk_num, last))
@@ -444,6 +463,7 @@ class Scriptures():
                 rest = f'1:1-{last}:{v}'
         else:
             rest = reform_series(rest)
+        all_ranges = []
         for chunk in rest.split(';'):
             ch = None
             for bit in chunk.split(','):
@@ -454,7 +474,8 @@ class Scriptures():
                 if not tup:
                     self._error_report(scripture, f'"{bit.strip()}" OUT OF RANGE')
                     return None
-                lst.append(tup)
+                all_ranges.append(tup)
+        lst = merge_ranges(all_ranges)
         return lst
 
     def code_scriptures(self, text):