use string representation when dumping variables

[nominatim.git] / nominatim / api / search / query.py

diff --git a/nominatim/api/search/query.py b/nominatim/api/search/query.py
index bc1f542d10148aeb79f3ee48240d5e4f7040dbc0..f2b18f873a8121fbdac79ea3c67b682826316e6b 100644 (file)
--- a/nominatim/api/search/query.py
+++ b/nominatim/api/search/query.py
@@ -7,7 +7,7 @@
 """
 Datastructures for a tokenized query.
 """
 """
 Datastructures for a tokenized query.
 """

-from typing import List, Tuple, Optional, NamedTuple
+from typing import List, Tuple, Optional, NamedTuple, Iterator

 from abc import ABC, abstractmethod
 import dataclasses
 import enum
 from abc import ABC, abstractmethod
 import dataclasses
 import enum


@@ -114,6 +114,24 @@ class TokenRange(NamedTuple):
     start: int
     end: int
 
     start: int
     end: int
 

+    def replace_start(self, new_start: int) -> 'TokenRange':
+        """ Return a new token range with the new start.
+        """
+        return TokenRange(new_start, self.end)
+
+
+    def replace_end(self, new_end: int) -> 'TokenRange':
+        """ Return a new token range with the new end.
+        """
+        return TokenRange(self.start, new_end)
+
+
+    def split(self, index: int) -> Tuple['TokenRange', 'TokenRange']:
+        """ Split the span into two spans at the given index.
+            The index must be within the span.
+        """
+        return self.replace_end(index), self.replace_start(index)
+

 
 @dataclasses.dataclass
 class TokenList:
 
 @dataclasses.dataclass
 class TokenList:


@@ -124,6 +142,13 @@ class TokenList:
     tokens: List[Token]
 
 
     tokens: List[Token]
 
 

+    def add_penalty(self, penalty: float) -> None:
+        """ Add the given penalty to all tokens in the list.
+        """
+        for token in self.tokens:
+            token.penalty += penalty
+
+

 @dataclasses.dataclass
 class QueryNode:
     """ A node of the querry representing a break between terms.
 @dataclasses.dataclass
 class QueryNode:
     """ A node of the querry representing a break between terms.


@@ -144,7 +169,10 @@ class QueryNode:
             and ending at the node 'end'. Returns 'None' if no such
             tokens exist.
         """
             and ending at the node 'end'. Returns 'None' if no such
             tokens exist.
         """

-        return next((t.tokens for t in self.starting if t.end == end and t.ttype == ttype), None)
+        for tlist in self.starting:
+            if tlist.end == end and tlist.ttype == ttype:
+                return tlist.tokens
+        return None

 
 
 @dataclasses.dataclass
 
 
 @dataclasses.dataclass


@@ -226,6 +254,14 @@ class QueryStruct:
                           for i in range(trange.start, trange.end)]
 
 
                           for i in range(trange.start, trange.end)]
 
 

+    def iter_token_lists(self) -> Iterator[Tuple[int, QueryNode, TokenList]]:
+        """ Iterator over all token lists in the query.
+        """
+        for i, node in enumerate(self.nodes):
+            for tlist in node.starting:
+                yield i, node, tlist
+
+

     def find_lookup_word_by_id(self, token: int) -> str:
         """ Find the first token with the given token ID and return
             its lookup word. Returns 'None' if no such token exists.
     def find_lookup_word_by_id(self, token: int) -> str:
         """ Find the first token with the given token ID and return
             its lookup word. Returns 'None' if no such token exists.