Merge pull request #3520 from lonvia/restrict-interpolation-range

[nominatim.git] / docs / customize / Tokenizers.md

diff --git a/docs/customize/Tokenizers.md b/docs/customize/Tokenizers.md
index 58606c29d0176822ce3364324520b34634a5e242..49e86a5009289cea7f12aea36202abbda1548737 100644 (file)
--- a/docs/customize/Tokenizers.md
+++ b/docs/customize/Tokenizers.md
@@ -17,6 +17,11 @@ they can be configured.
 
 ## Legacy tokenizer
 
 
 ## Legacy tokenizer
 

+!!! danger
+    The Legacy tokenizer is deprecated and will be removed in Nominatim 5.0.
+    If you still use a database with the legacy tokenizer, you must reimport
+    it using the ICU tokenizer below.
+

 The legacy tokenizer implements the analysis algorithms of older Nominatim
 versions. It uses a special Postgresql module to normalize names and queries.
 This tokenizer is automatically installed and used when upgrading an older
 The legacy tokenizer implements the analysis algorithms of older Nominatim
 versions. It uses a special Postgresql module to normalize names and queries.
 This tokenizer is automatically installed and used when upgrading an older


@@ -52,7 +57,7 @@ NOMINATIM_DATABASE_MODULE_PATH=<path to directory where nominatim.so resides>
 ```
 
 This is in particular useful when the database runs on a different server.
 ```
 
 This is in particular useful when the database runs on a different server.

-See [Advanced installations](../admin/Advanced-Installations.md#importing-nominatim-to-an-external-postgresql-database) for details.
+See [Advanced installations](../admin/Advanced-Installations.md#using-an-external-postgresql-database) for details.

 
 There are no other configuration options for the legacy tokenizer. All
 normalization functions are hard-coded.
 
 There are no other configuration options for the legacy tokenizer. All
 normalization functions are hard-coded.


@@ -102,7 +107,7 @@ Here is an example configuration file:
 ``` yaml
 normalization:
     - ":: lower ()"
 ``` yaml
 normalization:
     - ":: lower ()"

-    - "ß > 'ss'" # German szet is unimbigiously equal to double ss
+    - "ß > 'ss'" # German szet is unambiguously equal to double ss

 transliteration:
     - !include /etc/nominatim/icu-rules/extended-unicode-to-asccii.yaml
     - ":: Ascii ()"
 transliteration:
     - !include /etc/nominatim/icu-rules/extended-unicode-to-asccii.yaml
     - ":: Ascii ()"


@@ -128,7 +133,7 @@ The configuration file contains four sections:
 The normalization and transliteration sections each define a set of
 ICU rules that are applied to the names.
 
 The normalization and transliteration sections each define a set of
 ICU rules that are applied to the names.
 

-The **normalisation** rules are applied after sanitation. They should remove
+The **normalization** rules are applied after sanitation. They should remove

 any information that is not relevant for search at all. Usual rules to be
 applied here are: lower-casing, removing of special characters, cleanup of
 spaces.
 any information that is not relevant for search at all. Usual rules to be
 applied here are: lower-casing, removing of special characters, cleanup of
 spaces.


@@ -175,53 +180,67 @@ The following is a list of sanitizers that are shipped with Nominatim.
 
 ##### split-name-list
 
 
 ##### split-name-list
 

-::: nominatim.tokenizer.sanitizers.split_name_list
-    selection:
+::: nominatim_db.tokenizer.sanitizers.split_name_list
+    options:

         members: False
         members: False

-    rendering:

         heading_level: 6
         heading_level: 6

+        docstring_section_style: spacy

 
 ##### strip-brace-terms
 
 
 ##### strip-brace-terms
 

-::: nominatim.tokenizer.sanitizers.strip_brace_terms
-    selection:
+::: nominatim_db.tokenizer.sanitizers.strip_brace_terms
+    options:

         members: False
         members: False

-    rendering:

         heading_level: 6
         heading_level: 6

+        docstring_section_style: spacy

 
 ##### tag-analyzer-by-language
 
 
 ##### tag-analyzer-by-language
 

-::: nominatim.tokenizer.sanitizers.tag_analyzer_by_language
-    selection:
+::: nominatim_db.tokenizer.sanitizers.tag_analyzer_by_language
+    options:

         members: False
         members: False

-    rendering:

         heading_level: 6
         heading_level: 6

+        docstring_section_style: spacy

 
 ##### clean-housenumbers
 
 
 ##### clean-housenumbers
 

-::: nominatim.tokenizer.sanitizers.clean_housenumbers
-    selection:
+::: nominatim_db.tokenizer.sanitizers.clean_housenumbers
+    options:

         members: False
         members: False

-    rendering:

         heading_level: 6
         heading_level: 6

+        docstring_section_style: spacy

 
 ##### clean-postcodes
 
 
 ##### clean-postcodes
 

-::: nominatim.tokenizer.sanitizers.clean_postcodes
-    selection:
+::: nominatim_db.tokenizer.sanitizers.clean_postcodes
+    options:

         members: False
         members: False

-    rendering:

         heading_level: 6
         heading_level: 6

+        docstring_section_style: spacy

 
 ##### clean-tiger-tags
 
 
 ##### clean-tiger-tags
 

-::: nominatim.tokenizer.sanitizers.clean_tiger_tags
-    selection:
+::: nominatim_db.tokenizer.sanitizers.clean_tiger_tags
+    options:

         members: False
         members: False

-    rendering:

         heading_level: 6
         heading_level: 6

+        docstring_section_style: spacy
+
+#### delete-tags

 
 

+::: nominatim_db.tokenizer.sanitizers.delete_tags
+    options:
+        members: False
+        heading_level: 6
+        docstring_section_style: spacy

 
 

+#### tag-japanese
+
+::: nominatim_db.tokenizer.sanitizers.tag_japanese
+    options:
+        members: False
+        heading_level: 6
+        docstring_section_style: spacy

 
 #### Token Analysis
 
 
 #### Token Analysis
 


@@ -380,7 +399,7 @@ The analyzer cannot be customized.
 ##### Postcode token analyzer
 
 The analyzer `postcodes` is pupose-made to analyze postcodes. It supports
 ##### Postcode token analyzer
 
 The analyzer `postcodes` is pupose-made to analyze postcodes. It supports

-a 'lookup' varaint of the token, which produces variants with optional
+a 'lookup' variant of the token, which produces variants with optional

 spaces. Use together with the clean-postcodes sanitizer.
 
 The analyzer cannot be customized.
 spaces. Use together with the clean-postcodes sanitizer.
 
 The analyzer cannot be customized.