hans/Nominatim
1
0
Fork 1
mirror of https://github.com/osm-search/Nominatim.git synced 2026-02-26 11:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

rename use of category as POI search to near_item

Browse Source 
Use the term category only as a short-cut for "tuple of key and value".
This commit is contained in:
Sarah Hoffmann
2023-11-28 16:27:05 +01:00
parent 70dc4957dc
commit 3f72ca4bca
10 changed files with 62 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
nominatim/api/search/db_search_builder.py
View File

@@ -89,12 +89,12 @@ class SearchBuilder:
if sdata is None:
return
categories = self.get_search_categories(assignment)
near_items = self.get_near_items(assignment)
if assignment.name is None:
if categories and not sdata.postcodes:
sdata.qualifiers = categories
categories = None
if near_items and not sdata.postcodes:
sdata.qualifiers = near_items
near_items = None
builder = self.build_poi_search(sdata)
elif assignment.housenumber:
hnr_tokens = self.query.get_tokens(assignment.housenumber,
@@ -102,16 +102,16 @@ class SearchBuilder:
builder = self.build_housenumber_search(sdata, hnr_tokens, assignment.address)
else:
builder = self.build_special_search(sdata, assignment.address,
bool(categories))
bool(near_items))
else:
builder = self.build_name_search(sdata, assignment.name, assignment.address,
bool(categories))
bool(near_items))
if categories:
penalty = min(categories.penalties)
categories.penalties = [p - penalty for p in categories.penalties]
if near_items:
penalty = min(near_items.penalties)
near_items.penalties = [p - penalty for p in near_items.penalties]
for search in builder:
yield dbs.NearSearch(penalty + assignment.penalty, categories, search)
yield dbs.NearSearch(penalty + assignment.penalty, near_items, search)
else:
for search in builder:
search.penalty += assignment.penalty
@@ -339,15 +339,14 @@ class SearchBuilder:
return sdata
def get_search_categories(self,
assignment: TokenAssignment) -> Optional[dbf.WeightedCategories]:
""" Collect tokens for category search or use the categories
def get_near_items(self, assignment: TokenAssignment) -> Optional[dbf.WeightedCategories]:
""" Collect tokens for near items search or use the categories
requested per parameter.
Returns None if no category search is requested.
"""
if assignment.category:
if assignment.near_item:
tokens: Dict[Tuple[str, str], float] = {}
for t in self.query.get_tokens(assignment.category, TokenType.CATEGORY):
for t in self.query.get_tokens(assignment.near_item, TokenType.NEAR_ITEM):
cat = t.get_category()
if (not self.details.categories or cat in self.details.categories)\
and t.penalty < tokens.get(cat, 1000.0):

4
nominatim/api/search/icu_tokenizer.py
View File

@@ -184,13 +184,13 @@ class ICUQueryAnalyzer(AbstractQueryAnalyzer):
if row.type == 'S':
if row.info['op'] in ('in', 'near'):
if trange.start == 0:
query.add_token(trange, qmod.TokenType.CATEGORY, token)
query.add_token(trange, qmod.TokenType.NEAR_ITEM, token)
else:
query.add_token(trange, qmod.TokenType.QUALIFIER, token)
if trange.start == 0 or trange.end == query.num_token_slots():
token = copy(token)
token.penalty += 0.1 * (query.num_token_slots())
query.add_token(trange, qmod.TokenType.CATEGORY, token)
query.add_token(trange, qmod.TokenType.NEAR_ITEM, token)
else:
query.add_token(trange, DB_TO_TOKEN_TYPE[row.type], token)

8
nominatim/api/search/legacy_tokenizer.py
View File

@@ -107,15 +107,15 @@ class LegacyQueryAnalyzer(AbstractQueryAnalyzer):
for row in await self.lookup_in_db(lookup_words):
for trange in words[row.word_token.strip()]:
token, ttype = self.make_token(row)
if ttype == qmod.TokenType.CATEGORY:
if ttype == qmod.TokenType.NEAR_ITEM:
if trange.start == 0:
query.add_token(trange, qmod.TokenType.CATEGORY, token)
query.add_token(trange, qmod.TokenType.NEAR_ITEM, token)
elif ttype == qmod.TokenType.QUALIFIER:
query.add_token(trange, qmod.TokenType.QUALIFIER, token)
if trange.start == 0 or trange.end == query.num_token_slots():
token = copy(token)
token.penalty += 0.1 * (query.num_token_slots())
query.add_token(trange, qmod.TokenType.CATEGORY, token)
query.add_token(trange, qmod.TokenType.NEAR_ITEM, token)
elif ttype != qmod.TokenType.PARTIAL or trange.start + 1 == trange.end:
query.add_token(trange, ttype, token)
@@ -195,7 +195,7 @@ class LegacyQueryAnalyzer(AbstractQueryAnalyzer):
ttype = qmod.TokenType.POSTCODE
lookup_word = row.word_token[1:]
else:
ttype = qmod.TokenType.CATEGORY if row.operator in ('in', 'near')\
ttype = qmod.TokenType.NEAR_ITEM if row.operator in ('in', 'near')\
else qmod.TokenType.QUALIFIER
lookup_word = row.word
elif row.word_token.startswith(' '):

4
nominatim/api/search/query.py
View File

@@ -46,7 +46,7 @@ class TokenType(enum.Enum):
""" Country name or reference. """
QUALIFIER = enum.auto()
""" Special term used together with name (e.g. _Hotel_ Bellevue). """
CATEGORY = enum.auto()
NEAR_ITEM = enum.auto()
""" Special term used as searchable object(e.g. supermarket in ...). """
@@ -78,7 +78,7 @@ class PhraseType(enum.Enum):
return not is_full_phrase or ttype != TokenType.QUALIFIER
if self == PhraseType.AMENITY:
return ttype in (TokenType.WORD, TokenType.PARTIAL)\
or (is_full_phrase and ttype == TokenType.CATEGORY)\
or (is_full_phrase and ttype == TokenType.NEAR_ITEM)\
or (not is_full_phrase and ttype == TokenType.QUALIFIER)
if self == PhraseType.STREET:
return ttype in (TokenType.WORD, TokenType.PARTIAL, TokenType.HOUSENUMBER)

20
nominatim/api/search/token_assignment.py
View File

@@ -46,7 +46,7 @@ class TokenAssignment: # pylint: disable=too-many-instance-attributes
housenumber: Optional[qmod.TokenRange] = None
postcode: Optional[qmod.TokenRange] = None
country: Optional[qmod.TokenRange] = None
category: Optional[qmod.TokenRange] = None
near_item: Optional[qmod.TokenRange] = None
qualifier: Optional[qmod.TokenRange] = None
@@ -64,8 +64,8 @@ class TokenAssignment: # pylint: disable=too-many-instance-attributes
out.postcode = token.trange
elif token.ttype == qmod.TokenType.COUNTRY:
out.country = token.trange
elif token.ttype == qmod.TokenType.CATEGORY:
out.category = token.trange
elif token.ttype == qmod.TokenType.NEAR_ITEM:
out.near_item = token.trange
elif token.ttype == qmod.TokenType.QUALIFIER:
out.qualifier = token.trange
return out
@@ -109,7 +109,7 @@ class _TokenSequence:
"""
# Country and category must be the final term for left-to-right
return len(self.seq) > 1 and \
self.seq[-1].ttype in (qmod.TokenType.COUNTRY, qmod.TokenType.CATEGORY)
self.seq[-1].ttype in (qmod.TokenType.COUNTRY, qmod.TokenType.NEAR_ITEM)
def appendable(self, ttype: qmod.TokenType) -> Optional[int]:
@@ -165,22 +165,22 @@ class _TokenSequence:
if ttype == qmod.TokenType.COUNTRY:
return None if self.direction == -1 else 1
if ttype == qmod.TokenType.CATEGORY:
if ttype == qmod.TokenType.NEAR_ITEM:
return self.direction
if ttype == qmod.TokenType.QUALIFIER:
if self.direction == 1:
if (len(self.seq) == 1
and self.seq[0].ttype in (qmod.TokenType.PARTIAL, qmod.TokenType.CATEGORY)) \
and self.seq[0].ttype in (qmod.TokenType.PARTIAL, qmod.TokenType.NEAR_ITEM)) \
or (len(self.seq) == 2
and self.seq[0].ttype == qmod.TokenType.CATEGORY
and self.seq[0].ttype == qmod.TokenType.NEAR_ITEM
and self.seq[1].ttype == qmod.TokenType.PARTIAL):
return 1
return None
if self.direction == -1:
return -1
tempseq = self.seq[1:] if self.seq[0].ttype == qmod.TokenType.CATEGORY else self.seq
tempseq = self.seq[1:] if self.seq[0].ttype == qmod.TokenType.NEAR_ITEM else self.seq
if len(tempseq) == 0:
return 1
if len(tempseq) == 1 and self.seq[0].ttype == qmod.TokenType.HOUSENUMBER:
@@ -253,7 +253,7 @@ class _TokenSequence:
priors = sum(1 for t in self.seq[hnrpos+1:] if t.ttype == qmod.TokenType.PARTIAL)
if not self._adapt_penalty_from_priors(priors, 1):
return False
if any(t.ttype == qmod.TokenType.CATEGORY for t in self.seq):
if any(t.ttype == qmod.TokenType.NEAR_ITEM for t in self.seq):
self.penalty += 1.0
return True
@@ -368,7 +368,7 @@ class _TokenSequence:
# Postcode or country-only search
if not base.address:
if not base.housenumber and (base.postcode or base.country or base.category):
if not base.housenumber and (base.postcode or base.country or base.near_item):
log().comment('postcode/country search')
yield dataclasses.replace(base, penalty=self.penalty)
else: