Refactored PhraseAnalyzedQuery

src/morphodict/phrase_translate/types.py

@@ -0,0 +1,53 @@
+import re
+from morphodict.phrase_translate.fst import source_phrase_analyses
+
+# e.g., " swim +V+AI+Prt+3Pl"
+PHRASE_ANALYSIS_OUTPUT_RE = re.compile(
+    r"""
+                        \s*             # leading blank space(s) from flag diacritics
+                        (?P<query>.*)
+                        \s
+                        (?P<tags>\+[^\ ]+)
+                    """,
+    re.VERBOSE,
+)
+
+class PhraseAnalyzedQuery:
+    """A structured object holding pieces of, and info about, a phrase query.
+
+    >>> PhraseAnalyzedQuery("they swam").filtered_query
+    'swim'
+    >>> PhraseAnalyzedQuery("they swam").has_tags
+    True
+    >>> PhraseAnalyzedQuery("they swam").tags
+    ['+V', '+AI', '+Prt', '+3Pl']
+    >>> PhraseAnalyzedQuery("excellent").has_tags
+    False
+    """
+
+    def __init__(self, query: str, add_verbose_message=None):
+        self.query = query
+        self.has_tags = False
+        self.filtered_query = None
+        self.tags = None
+        phrase_analyses: list[str] = source_phrase_analyses(query)
+
+        if add_verbose_message:
+            add_verbose_message(phrase_analyses=phrase_analyses)
+
+        if len(phrase_analyses) != 1:
+            return
+
+        phrase_analysis = phrase_analyses[0]
+        if "+?" in phrase_analysis:
+            return
+
+        if not (match := PHRASE_ANALYSIS_OUTPUT_RE.fullmatch(phrase_analysis)):
+            return
+
+        self.filtered_query = match["query"]
+        self.has_tags = True
+        self.tags = ["+" + t for t in match["tags"].split("+") if t]
+
+    def __repr__(self):
+        return f"<PhraseAnalyzedQuery {self.__dict__!r}>"

src/morphodict/search/espt.py

@@ -13,7 +13,7 @@
 )
 
 from morphodict.search.types import Result
-from morphodict.phrase_translate.fst import source_phrase_analyses
+from morphodict.phrase_translate.types import PhraseAnalyzedQuery
 from morphodict.analysis import RichAnalysis
 from morphodict.analysis.tag_map import UnknownTagError
 from morphodict.lexicon.models import Wordform
@@ -192,54 +192,4 @@ def _generate_inflected_results(self) -> list[_EipResult]:
         return results
 
 
-# e.g., " swim +V+AI+Prt+3Pl"
-PHRASE_ANALYSIS_OUTPUT_RE = re.compile(
-    r"""
-                        \s*             # leading blank space(s) from flag diacritics
-                        (?P<query>.*)
-                        \s
-                        (?P<tags>\+[^\ ]+)
-                    """,
-    re.VERBOSE,
-)
-
-
-class PhraseAnalyzedQuery:
-    """A structured object holding pieces of, and info about, a phrase query.
-
-    >>> PhraseAnalyzedQuery("they swam").filtered_query
-    'swim'
-    >>> PhraseAnalyzedQuery("they swam").has_tags
-    True
-    >>> PhraseAnalyzedQuery("they swam").tags
-    ['+V', '+AI', '+Prt', '+3Pl']
-    >>> PhraseAnalyzedQuery("excellent").has_tags
-    False
-    """
-
-    def __init__(self, query: str, add_verbose_message=None):
-        self.query = query
-        self.has_tags = False
-        self.filtered_query = None
-        self.tags = None
-        phrase_analyses: list[str] = source_phrase_analyses(query)
-
-        if add_verbose_message:
-            add_verbose_message(phrase_analyses=phrase_analyses)
-
-        if len(phrase_analyses) != 1:
-            return
-
-        phrase_analysis = phrase_analyses[0]
-        if "+?" in phrase_analysis:
-            return
-
-        if not (match := PHRASE_ANALYSIS_OUTPUT_RE.fullmatch(phrase_analysis)):
-            return
-
-        self.filtered_query = match["query"]
-        self.has_tags = True
-        self.tags = ["+" + t for t in match["tags"].split("+") if t]
 
-    def __repr__(self):
-        return f"<PhraseAnalyzedQuery {self.__dict__!r}>"