From c2c547e7867742b06cd97c95210c864b0ed9789f Mon Sep 17 00:00:00 2001
From: aldacron <aldacron@users.noreply.github.com>
Date: Mon, 15 May 2017 11:14:01 -0700
Subject: [PATCH] some more elasticsearch work, including index mapping and
 analyzer

---
 create_es.sh     |  3 ++
 es_mapping.yml   | 91 ++++++++++++++++++++++++++++++++++++++++++++++++
 import_to_es.py  |  5 +--
 nyaa/routes.py   |  2 +-
 requirements.txt | 20 +----------
 5 files changed, 97 insertions(+), 24 deletions(-)
 create mode 100755 create_es.sh
 create mode 100644 es_mapping.yml

diff --git a/create_es.sh b/create_es.sh
new file mode 100755
index 0000000..2b83620
--- /dev/null
+++ b/create_es.sh
@@ -0,0 +1,3 @@
+#!/usr/bin/env bash
+
+curl -v -XPUT 'localhost:9200/nyaav2?pretty' -H"Content-Type: application/yaml" --data-binary @es_mapping.yml
diff --git a/es_mapping.yml b/es_mapping.yml
new file mode 100644
index 0000000..9085ec2
--- /dev/null
+++ b/es_mapping.yml
@@ -0,0 +1,91 @@
+---
+# CREATE DTABASE/TABLE equivalent for elasticsearch, in yaml
+# fo inline comments.
+settings:
+  analysis:
+    analyzer:
+      my_search_analyzer:
+        type: custom
+        tokenizer: standard
+        char_filter:
+          - my_char_filter
+        filter:
+          - standard
+          - lowercase
+      my_index_analyzer:
+        type: custom
+        tokenizer: standard
+        char_filter:
+          - my_char_filter
+        filter:
+          - lowercase
+          - my_ngram
+    filter:
+      my_ngram:
+        type: edgeNGram
+        min_gram: 1
+        max_gram: 15
+    char_filter:
+      my_char_filter:
+        type: mapping
+        mappings: ["-=>_", "!=>_"]
+  index:
+    # we're running a single es node, so no sharding necessary,
+    # plus replicas don't really help either.
+    number_of_shards: 1
+    number_of_replicas : 0
+    mapper:
+      # disable elasticsearch's "helpful" autoschema
+      dynamic: false
+    # since we disabled the _all field, default query the
+    # name of the torrent.
+    query:
+      default_field: display_name
+mappings:
+  torrent:
+    # don't want everything concatenated
+    _all:
+      enabled: false
+    properties:
+      id:
+        type: long
+      display_name:
+        # TODO could do a fancier tokenizer here to parse out the
+        # the scene convention of stuff in brackets, plus stuff like k-on
+        type: text
+        analyzer: my_index_analyzer
+        fielddata: true
+      created_time:
+        type: date
+        # Only in the ES index for generating magnet links
+      info_hash:
+        enabled: false
+      filesize:
+        type: long
+      anonymous:
+        type: boolean
+      trusted:
+        type: boolean
+      remake:
+        type: boolean
+      complete:
+        type: boolean
+      hidden:
+        type: boolean
+      deleted:
+        type: boolean
+      has_torrent:
+        type: boolean
+      download_count:
+        type: long
+      leech_count:
+        type: long
+      seed_count:
+        type: long
+      # these ids are really only for filtering, thus keyword
+      uploader_id:
+        type: keyword
+      main_category_id:
+        type: keyword
+      sub_category_id:
+        type: keyword
\ No newline at end of file
diff --git a/import_to_es.py b/import_to_es.py
index e714da5..046bde6 100644
--- a/import_to_es.py
+++ b/import_to_es.py
@@ -41,8 +41,6 @@ def mk_es(t):
             "id": t.id,
             "display_name": t.display_name,
             "created_time": t.created_time,
-            "updated_time": t.updated_time,
-            "description": t.description,
             # not analyzed but included so we can render magnet links
             # without querying sql again.
             "info_hash": t.info_hash.hex(),
@@ -61,8 +59,7 @@ def mk_es(t):
             "hidden": bool(t.hidden),
             "deleted": bool(t.deleted),
             "has_torrent": t.has_torrent,
-            # XXX last_updated isn't initialized
-            "stats_last_updated": t.stats.last_updated or t.created_time,
+            # Stats
             "download_count": t.stats.download_count,
             "leech_count": t.stats.leech_count,
             "seed_count": t.stats.seed_count,
diff --git a/nyaa/routes.py b/nyaa/routes.py
index 3e87a2a..758635a 100644
--- a/nyaa/routes.py
+++ b/nyaa/routes.py
@@ -148,7 +148,7 @@ def search(term='', user=None, sort='id', order='desc', category='0_0', quality_
     s = Search(using=es_client, index='nyaav2')
     if term:
         query = db.session.query(models.TorrentNameSearch)
-        s = s.query("query_string", default_field="display_name", default_operator="AND", query=term)
+        s = s.query("simple_query_string", analyzer="my_search_analyzer", default_operator="AND", query=term)
     else:
         query = models.Torrent.query
 
diff --git a/requirements.txt b/requirements.txt
index dbf234d..af89eab 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -33,24 +33,6 @@ webassets==0.12.1
 Werkzeug==0.12.1
 WTForms==2.1
 ## The following requirements were added by pip freeze:
-decorator==4.0.11
 elasticsearch==5.3.0
 elasticsearch-dsl==5.2.0
-ipython==6.0.0
-ipython-genutils==0.2.0
-jedi==0.10.2
-mysql-replication==0.13
-pexpect==4.2.1
-pickleshare==0.7.4
-pkg-resources==0.0.0
-progressbar2==3.20.0
-prompt-toolkit==1.0.14
-ptyprocess==0.5.1
-Pygments==2.2.0
-PyMySQL==0.7.11
-python-dateutil==2.6.0
-python-utils==2.1.0
-simplegeneric==0.8.1
-traitlets==4.3.2
-urllib3==1.21.1
-wcwidth==0.1.7
+progressbar2==3.20.0
\ No newline at end of file