Add solr schema to repo

README.md

@@ -21,16 +21,7 @@ The search index uses [Solr](http://lucene.apache.org/solr/), so you will have t
 If you are running it on a non-standard host or port, you will have to adjust the configuration. See the
 [NelmioSolariumBundle](https://github.com/nelmio/NelmioSolariumBundle) for more details.
 
-You will also have to configure Solr. The standard `schema.xml` already covers most fields like `title` and
-`description`. The following need to be added though:
-
-    <fields>
-        ...
-
-        <field name="tags" type="text_general" indexed="true" stored="true" multiValued="true"/>
-
-        ....
-    </fields>
+You will also have to configure Solr. Use the `schema.xml` provided in the doc/ directory for that.
 
 To index packages, just run `app/console packagist:index`. It is recommended to set up a cron job for
 this command, and have it run every few minutes.

doc/schema.xml

@@ -0,0 +1,272 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<schema name="packagist" version="1.4">
+  <types>
+    <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
+    <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
+    <!-- boolean type: "true" or "false" -->
+    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
+    <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
+    <fieldtype name="binary" class="solr.BinaryField"/>
+
+    <!-- The optional sortMissingLast and sortMissingFirst attributes are
+         currently supported on types that are sorted internally as strings
+         and on numeric types.
+	       This includes "string","boolean", and, as of 3.5 (and 4.x),
+	       int, float, long, date, double, including the "Trie" variants.
+       - If sortMissingLast="true", then a sort on this field will cause documents
+         without the field to come after documents with the field,
+         regardless of the requested sort order (asc or desc).
+       - If sortMissingFirst="true", then a sort on this field will cause documents
+         without the field to come before documents with the field,
+         regardless of the requested sort order.
+       - If sortMissingLast="false" and sortMissingFirst="false" (the default),
+         then default lucene sorting will be used which places docs without the
+         field first in an ascending sort and last in a descending sort.
+    -->    
+
+    <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+    <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+    <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+    <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+
+    <fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/>
+
+    <!-- A Trie based date field for faster date range queries and date faceting. -->
+    <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
+
+    <!-- A edge-ngram'd text field that can be used for wildcard matching -->
+    <fieldType name="text_edgengram" class="solr.TextField" positionIncrementGap="100">
+        <analyzer type="index">
+            <tokenizer class="solr.KeywordTokenizerFactory"/>
+            <filter class="solr.LowerCaseFilterFactory"/>
+            <filter class="solr.EdgeNGramFilterFactory" minGramSize="1" maxGramSize="100" />
+        </analyzer>
+        <analyzer type="query">
+            <tokenizer class="solr.KeywordTokenizerFactory"/>
+            <filter class="solr.LowerCaseFilterFactory"/>
+        </analyzer>
+    </fieldType>
+
+    <!-- A general text field that has reasonable, generic
+         cross-language defaults: it tokenizes with StandardTokenizer,
+	 removes stop words from case-insensitive "stopwords.txt"
+	 (empty by default), and down cases.  At query time only, it
+	 also applies synonyms. -->
+    <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
+        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Just like text_general except it reverses the characters of
+	 each token, to enable more efficient leading wildcard queries. -->
+    <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
+           maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English: it
+         tokenizes with StandardTokenizer, removes English stop words
+         (stopwords_en.txt), down cases, protects words from protwords.txt, and
+         finally applies Porter's stemming.  The query time analyzer
+         also applies synonyms from synonyms.txt. -->
+    <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        -->
+        <!-- Case insensitive stop word removal.
+          add enablePositionIncrements=true in both the index and query
+          analyzers to leave a 'gap' for more accurate phrase queries.
+        -->
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="stopwords_en.txt"
+                enablePositionIncrements="true"
+                />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+	<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+	-->
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="stopwords_en.txt"
+                enablePositionIncrements="true"
+                />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+	<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+	-->
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English, plus
+	 aggressive word-splitting and autophrase features enabled.
+	 This field is just like text_en, except it adds
+	 WordDelimiterFilter to enable splitting and matching of
+	 words on case-change, alpha numeric boundaries, and
+	 non-alphanumeric chars.  This means certain compound word
+	 cases will work, for example query "wi fi" will match
+	 document "WiFi" or "wi-fi".  However, other cases will still
+	 not match, for example if the query is "wifi" and the
+	 document is "wi fi" or if the query is "wi-fi" and the
+	 document is "wifi".
+        -->
+    <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+      <analyzer type="index">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        -->
+        <!-- Case insensitive stop word removal.
+          add enablePositionIncrements=true in both the index and query
+          analyzers to leave a 'gap' for more accurate phrase queries.
+        -->
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="stopwords_en.txt"
+                enablePositionIncrements="true"
+                />
+        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="stopwords_en.txt"
+                enablePositionIncrements="true"
+                />
+        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
+         but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
+    <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
+      </analyzer>
+    </fieldtype>
+
+    <!-- since fields of this type are by default not stored or indexed,
+         any data added to them will be ignored outright.  --> 
+    <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
+ </types>
+
+ <fields>
+   <!-- Valid attributes for fields:
+     name: mandatory - the name for the field
+     type: mandatory - the name of a previously defined type from the 
+       <types> section
+     indexed: true if this field should be indexed (searchable or sortable)
+     stored: true if this field should be retrievable
+     multiValued: true if this field may contain multiple values per document
+     omitNorms: (expert) set to true to omit the norms associated with
+       this field (this disables length normalization and index-time
+       boosting for the field, and saves some memory).  Only full-text
+       fields or fields that need an index-time boost need norms.
+     termVectors: [false] set to true to store the term vector for a
+       given field.
+       When using MoreLikeThis, fields used for similarity should be
+       stored for best performance.
+     termPositions: Store position information with the term vector.  
+       This will increase storage costs.
+     termOffsets: Store offset information with the term vector. This 
+       will increase storage costs.
+     default: a value that should be used if no value is specified
+       when adding a document.
+   -->
+
+   <field name="id" type="string" indexed="true" stored="true" required="true" /> 
+   <field name="name" type="text_general_rev" indexed="true" stored="true"/>
+   <field name="description" type="text_general_rev" indexed="true" stored="true"/>
+   <field name="tags" type="text_general_rev" indexed="true" stored="true" multiValued="true"/>
+   
+   <!-- catchall field, containing all other searchable text fields (implemented
+        via copyField further on in this schema  -->
+   <field name="text" type="text_en" indexed="true" stored="false" multiValued="true"/>
+   
+   <!-- extra name field allowing dashes to be omitted/misplaced -->
+   <field name="name_split" type="text_en_splitting_tight" indexed="true" stored="false" />
+
+   <!-- extra catchall for ngram searches -->
+   <field name="text_ngram" type="text_edgengram" indexed="true" stored="false" multiValued="true" />
+ </fields>
+
+ <!-- Field to use to determine and enforce document uniqueness. 
+      Unless this field is marked with required="false", it will be a required field
+   -->
+ <uniqueKey>id</uniqueKey>
+
+ <!-- field for the QueryParser to use when an explicit fieldname is absent -->
+ <defaultSearchField>text</defaultSearchField>
+
+ <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
+ <solrQueryParser defaultOperator="OR"/>
+  <!-- copyField commands copy one field to another at the time a document
+        is added to the index.  It's used either to index the same field differently,
+        or to add multiple fields to the same field for easier/faster searching.  -->
+
+   <copyField source="name" dest="text"/>
+   <copyField source="description" dest="text"/>
+   <copyField source="tags" dest="text"/>
+
+   <copyField source="name" dest="name_split"/>
+
+   <copyField source="name" dest="text_ngram"/>
+   <copyField source="description" dest="text_ngram"/>
+   <copyField source="tags" dest="text_ngram"/>
+</schema>