add inner word break penalty

[nominatim.git] / src / nominatim_api / search / query.py

diff --git a/src/nominatim_api/search/query.py b/src/nominatim_api/search/query.py
index 02ebbb5b9d7b6f690af9bdcba466151d57117d1a..aa16943133f294d6b59e61008969513fcc0400d9 100644 (file)
--- a/src/nominatim_api/search/query.py
+++ b/src/nominatim_api/search/query.py
@@ -21,7 +21,13 @@ class BreakType(enum.Enum):
     END = '>'
     """ End of the query. """
     PHRASE = ','
-    """ Break between two phrases. """
+    """ Hard break between two phrases. Address parts cannot cross hard
+        phrase boundaries."""
+    SOFT_PHRASE = ':'
+    """ Likely break between two phrases. Address parts should not cross soft
+        phrase boundaries. Soft breaks can be inserted by a preprocessor
+        that is analysing the input string.
+    """
     WORD = ' '
     """ Break between words. """
     PART = '-'
@@ -116,6 +122,7 @@ class TokenRange:
     """
     start: int
     end: int
+    penalty: Optional[float] = None
 
     def __lt__(self, other: 'TokenRange') -> bool:
         return self.end <= other.start