aboutsummaryrefslogtreecommitdiffstats
path: root/extra/elasticsearch/file_schema.json
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@robocracy.org>2020-01-30 00:51:56 -0800
committerBryan Newbold <bnewbold@robocracy.org>2020-01-30 00:52:01 -0800
commitb7404fb0f696807db3a92bc2c4c73c2d208e59ef (patch)
treee5b74f29fd183427543789ec512a31c6978518e8 /extra/elasticsearch/file_schema.json
parent59912583926077260d99a9bf77a938c2215eb6c8 (diff)
downloadfatcat-b7404fb0f696807db3a92bc2c4c73c2d208e59ef.tar.gz
fatcat-b7404fb0f696807db3a92bc2c4c73c2d208e59ef.zip
ES schemas: make keywords case-insensitive by default
But not applying asciifolding; don't see any need to do so?
Diffstat (limited to 'extra/elasticsearch/file_schema.json')
-rw-r--r--extra/elasticsearch/file_schema.json34
1 files changed, 23 insertions, 11 deletions
diff --git a/extra/elasticsearch/file_schema.json b/extra/elasticsearch/file_schema.json
index a0ac3346..9c8ee64c 100644
--- a/extra/elasticsearch/file_schema.json
+++ b/extra/elasticsearch/file_schema.json
@@ -8,6 +8,18 @@
"tokenizer": "standard",
"filter": [ "lowercase", "asciifolding" ]
}
+ },
+ "normalizer": {
+ "default": {
+ "type": "custom",
+ "char_filter": [],
+ "filter": ["lowercase"]
+ },
+ "caseSensitive": {
+ "type": "custom",
+ "char_filter": [],
+ "filter": []
+ }
}
}
}
@@ -15,21 +27,21 @@
"mappings": {
"file": {
"properties": {
- "ident": { "type": "keyword", "doc_values": false },
- "state": { "type": "keyword" },
- "revision": { "type": "keyword", "doc_values": false },
+ "ident": { "type": "keyword", "normalizer": "default", "doc_values": false },
+ "state": { "type": "keyword", "normalizer": "default" },
+ "revision": { "type": "keyword", "normalizer": "default", "doc_values": false },
- "release_ids": { "type": "keyword", "doc_values": false },
+ "release_ids": { "type": "keyword", "normalizer": "default", "doc_values": false },
"release_count": { "type": "integer" },
- "mimetype": { "type": "keyword" },
+ "mimetype": { "type": "keyword", "normalizer": "default" },
"size_bytes": { "type": "integer" },
- "sha1": { "type": "keyword", "doc_values": false },
- "sha256": { "type": "keyword", "doc_values": false },
- "md5": { "type": "keyword", "doc_values": false },
+ "sha1": { "type": "keyword", "normalizer": "default", "doc_values": false },
+ "sha256": { "type": "keyword", "normalizer": "default", "doc_values": false },
+ "md5": { "type": "keyword", "normalizer": "default", "doc_values": false },
- "domains": { "type": "keyword" },
- "hosts": { "type": "keyword" },
- "rels": { "type": "keyword" },
+ "domains": { "type": "keyword", "normalizer": "default" },
+ "hosts": { "type": "keyword", "normalizer": "default" },
+ "rels": { "type": "keyword", "normalizer": "default" },
"in_ia": { "type": "boolean" },
"in_ia_petabox": { "type": "boolean" },