From 1aec5a3da74073c31370c8c434d963efc269422f Mon Sep 17 00:00:00 2001
From: Yonik Seeley <yonik@apache.org>
Date: Thu, 23 Feb 2006 19:18:22 +0000
Subject: [PATCH] changes in the schema, and some sample docs

git-svn-id: https://svn.apache.org/repos/asf/incubator/solr/trunk@380201 13f79535-47bb-0310-9956-ffa450edef68
---
 example/conf/schema.xml            | 66 +++++++++++++++++++++++-------
 example/exampledocs/hd.xml         | 29 +++++++++++++
 example/exampledocs/ipod_other.xml | 33 +++++++++++++++
 example/exampledocs/ipod_video.xml | 18 ++++++++
 example/exampledocs/mem.xml        | 41 +++++++++++++++++++
 example/exampledocs/monitor.xml    | 14 +++++++
 example/exampledocs/monitor2.xml   | 13 ++++++
 example/exampledocs/mp500.xml      | 22 ++++++++++
 example/exampledocs/post.sh        | 12 ++++++
 example/exampledocs/sd500.xml      | 16 ++++++++
 example/exampledocs/vidcard.xml    | 35 ++++++++++++++++
 11 files changed, 285 insertions(+), 14 deletions(-)
 create mode 100755 example/exampledocs/hd.xml
 create mode 100755 example/exampledocs/ipod_other.xml
 create mode 100644 example/exampledocs/ipod_video.xml
 create mode 100755 example/exampledocs/mem.xml
 create mode 100755 example/exampledocs/monitor.xml
 create mode 100755 example/exampledocs/monitor2.xml
 create mode 100755 example/exampledocs/mp500.xml
 create mode 100755 example/exampledocs/post.sh
 create mode 100755 example/exampledocs/sd500.xml
 create mode 100755 example/exampledocs/vidcard.xml

diff --git a/example/conf/schema.xml b/example/conf/schema.xml
index 455e12a3c52..89ec9f00eaa 100755
--- a/example/conf/schema.xml
+++ b/example/conf/schema.xml
@@ -66,8 +66,10 @@
          matching across fields.
      -->
 
+     <!-- Standard analyzer commonly used by Lucene developers
+     -->
     <!-- Standard analyzer commonly used by Lucene developers -->
-    <fieldtype name="text_lu" class="solr.TextField" positionIncrementGap="10">
+    <fieldtype name="text_lu" class="solr.TextField" positionIncrementGap="100">
       <analyzer>
         <tokenizer class="solr.StandardTokenizerFactory"/>
         <filter class="solr.StandardFilterFactory"/>
@@ -76,9 +78,15 @@
         <filter class="solr.EnglishPorterFilterFactory"/>
       </analyzer>
     </fieldtype>
-
+    <!-- One could also specify an existing Analyzer implementation in Java 
+         via the class attribute on the analyzer element:
+    <fieldtype name="text_lu" class="solr.TextField">
+      <analyzer class="org.apache.lucene.analysis.snowball.SnowballAnalyzer"/>
+    </fieldType>
+    -->
+    
     <!-- A text field that only splits on whitespace for more exact matching -->
-    <fieldtype name="text_ws" class="solr.TextField" positionIncrementGap="10">
+    <fieldtype name="text_ws" class="solr.TextField" positionIncrementGap="100">
       <analyzer>
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
       </analyzer>
@@ -86,9 +94,9 @@
 
     <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
         words on case-change, alpha numeric boundaries, and non-alphanumeric chars
-        so that a query of "wifi" or "wi fi" could match a document containing Wi-Fi.
+        so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
         Synonyms and stopwords are customized by external files, and stemming is enabled -->
-    <fieldtype name="text" class="solr.TextField" positionIncrementGap="10">
+    <fieldtype name="text" class="solr.TextField" positionIncrementGap="100">
       <analyzer type="index">
           <tokenizer class="solr.WhitespaceTokenizerFactory"/>
           <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
@@ -107,6 +115,20 @@
       </analyzer>
     </fieldtype>
 
+
+    <!-- Less flexible matching, but less false matches.  Probably not ideal for product names
+i        but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
+    <fieldtype name="textTight" class="solar.TextField" positionIncrementGap="100" >
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true"/>
+        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+      </analyzer>
+    </fieldtype>
+
  </types>
 
 
@@ -122,15 +144,26 @@
    -->
 
    <field name="id" type="string" indexed="true" stored="true"/>
-   <field name="date" type="date" indexed="true" stored="true"/>
-   <field name="title" type="text" indexed="true" stored="true"/>
-   <field name="subject" type="text" indexed="true" stored="true"/>
-   <field name="body" type="text" indexed="true" stored="true"/>
+   <field name="sku" type="textTight" indexed="true" stored="true"/>
+   <field name="name" type="text" indexed="true" stored="true"/>
+   <field name="manu" type="text" indexed="true" stored="true"/>
+   <field name="cat" type="text_ws" indexed="true" stored="true" multiValued="true"/>
+   <field name="features" type="text" indexed="true" stored="true" multiValued="true"/>
+   <field name="includes" type="text" indexed="true" stored="true"/>
+
+   <field name="weight" type="sfloat" indexed="true" stored="true"/>
+   <field name="price"  type="sfloat" indexed="true" stored="true"/>
+   <field name="popularity" type="sint" indexed="true" stored="true"/>
+   <field name="inStock" type="boolean" indexed="true" stored="true"/>
 
    <!-- catchall field, containing all other searchable text fields (implemented
         via copyField further on in this schema  -->
    <field name="text" type="text" indexed="true" stored="false" multiValued="true"/>
 
+   <!-- non-tokenized version of manufacturer to make it easier to sort or group
+        results by manufacturer.  copied from "manu" via copyField -->
+   <field name="manu_exact" type="string" indexed="true" stored="false"/>
+
 
    <!-- Dynamic field definitions.  If a field name is not found, dynamicFields
         will be used if the name matches any of the patterns.
@@ -149,8 +182,7 @@
    <dynamicField name="*_dt" type="date"    indexed="true"  stored="true"/>
  </fields>
 
- <!-- field to use to determine document uniqueness... used when
-      overwriting one document with another -->
+ <!-- field to use to determine and enforce document uniqueness. -->
  <uniqueKey>id</uniqueKey>
 
  <!-- field for the QueryParser to use when an explicit fieldname is absent -->
@@ -159,9 +191,15 @@
   <!-- 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 different
         ways, or to add multiple fields to the same field for easier/faster searching.  -->
-   <copyField source="title" dest="text"/>
-   <copyField source="subject" dest="text"/>
-   <copyField source="body" dest="text"/>
+   <copyField source="id" dest="sku"/>
+
+   <copyField source="cat" dest="text"/>
+   <copyField source="name" dest="text"/>
+   <copyField source="manu" dest="text"/>
+   <copyField source="features" dest="text"/>
+   <copyField source="includes" dest="text"/>
+
+   <copyField source="manu" dest="manu_exact"/>
 
  <!-- Similarity is the scoring routine for each document vs a query.
       A custom similarity may be specified here, but the default is fine
diff --git a/example/exampledocs/hd.xml b/example/exampledocs/hd.xml
new file mode 100755
index 00000000000..57d9f474f45
--- /dev/null
+++ b/example/exampledocs/hd.xml
@@ -0,0 +1,29 @@
+<add>
+<doc>
+  <field name="id">SP2514N</field>
+  <field name="name">Samsung SpinPoint P120 SP2514N - hard drive - 250 GB - ATA-133</field>
+  <field name="manu">Samsung Electronics Co. Ltd.</field>
+  <field name="cat">electronics</field>
+  <field name="cat">hard drive</field>
+  <field name="features">7200RPM, 8MB cache, IDE Ultra ATA-133</field>
+  <field name="features">NoiseGuard, SilentSeek technology, Fluid Dynamic Bearing (FDB) motor</field>
+  <field name="price">92</field>
+  <field name="popularity">6</field>
+  <field name="inStock">true</field>
+</doc>
+
+<doc>
+  <field name="id">6H500F0</field>
+  <field name="name">Maxtor DiamondMax 11 - hard drive - 500 GB - SATA-300</field>
+  <field name="manu">Maxtor Corp.</field>
+  <field name="cat">electronics</field>
+  <field name="cat">hard drive</field>
+  <field name="features">SATA 3.0Gb/s, NCQ</field>
+  <field name="features">8.5ms seek</field>
+  <field name="features">16MB cache</field>
+  <field name="price">350</field>
+  <field name="popularity">6</field>
+  <field name="inStock">true</field>
+</doc>
+</add>
+
diff --git a/example/exampledocs/ipod_other.xml b/example/exampledocs/ipod_other.xml
new file mode 100755
index 00000000000..374c2f5ba20
--- /dev/null
+++ b/example/exampledocs/ipod_other.xml
@@ -0,0 +1,33 @@
+<add>
+
+<doc>
+  <field name="id">F8V7067-APL-KIT</field>
+  <field name="name">Belkin Mobile Power Cord for iPod w/ Dock</field>
+  <field name="manu">Belkin</field>
+  <field name="cat">electronics</field>
+  <field name="cat">connector</field>
+  <field name="features">car power adapter, white</field>
+  <field name="weight">4</field>
+  <field name="price">19.95</field>
+  <field name="popularity">1</field>
+  <field name="inStock">false</field>
+</doc>
+
+<doc>
+  <field name="id">IW-02</field>
+  <field name="name">iPod &amp; iPod Mini USB 2.0 Cable</field>
+  <field name="manu">Belkin</field>
+  <field name="cat">electronics</field>
+  <field name="cat">connector</field>
+  <field name="features">car power adapter for iPod, white</field>
+  <field name="weight">2</field>
+  <field name="price">11.50</field>
+  <field name="popularity">1</field>
+  <field name="inStock">false</field>
+</doc>
+
+
+</add>
+
+
+
diff --git a/example/exampledocs/ipod_video.xml b/example/exampledocs/ipod_video.xml
new file mode 100644
index 00000000000..75c3996860b
--- /dev/null
+++ b/example/exampledocs/ipod_video.xml
@@ -0,0 +1,18 @@
+<add><doc>
+  <field name="id">MA147LL/A</field>
+  <field name="name">Apple 60 GB iPod with Video Playback Black</field>
+  <field name="manu">Apple Computer Inc.</field>
+  <field name="cat">electronics</field>
+  <field name="cat">music</field>
+  <field name="features">iTunes, Podcasts, Audiobooks</field>
+  <field name="features">Stores up to 15,000 songs, 25,000 photos, or 150 hours of video</field>
+  <field name="features">2.5-inch, 320x240 color TFT LCD display with LED backlight</field>
+  <field name="features">Up to 20 hours of battery life</field>
+  <field name="features">Plays AAC, MP3, WAV, AIFF, Audible, Apple Lossless, H.264 video</field>
+  <field name="features">Notes, Calendar, Phone book, Hold button, Date display, Photo wallet, Built-in games, JPEG photo playback, Upgradeable firmware, USB 2.0 compatibility, Playback speed control, Rechargeable capability, Battery level indication</field>
+  <field name="includes">earbud headphones, USB cable</field>
+  <field name="weight">5.5</field>
+  <field name="price">399.00</field>
+  <field name="popularity">10</field>
+  <field name="inStock">true</field>
+</doc></add>
diff --git a/example/exampledocs/mem.xml b/example/exampledocs/mem.xml
new file mode 100755
index 00000000000..b16af45e09b
--- /dev/null
+++ b/example/exampledocs/mem.xml
@@ -0,0 +1,41 @@
+<add>
+<doc>
+  <field name="id">TWINX2048-3200PRO</field>
+  <field name="name">CORSAIR XMS 2GB (2 x 1GB) 184-Pin DDR SDRAM Unbuffered DDR 400 (PC 3200) Dual Channel Kit System Memory - Retail</field>
+  <field name="manu">Corsair Microsystems Inc.</field>
+  <field name="cat">electronics</field>
+  <field name="cat">memory</field>
+  <field name="features">CAS latency 2,	2-3-3-6 timing, 2.75v, unbuffered, heat-spreader</field>
+  <field name="price">185</field>
+  <field name="popularity">5</field>
+  <field name="inStock">true</field>
+</doc>
+
+<doc>
+  <field name="id">VS1GB400C3</field>
+  <field name="name">CORSAIR ValueSelect 1GB 184-Pin DDR SDRAM Unbuffered DDR 400 (PC 3200) System Memory - Retail</field>
+  <field name="manu">Corsair Microsystems Inc.</field>
+  <field name="cat">electronics</field>
+  <field name="cat">memory</field>
+  <field name="price">74.99</field>
+  <field name="popularity">7</field>
+  <field name="inStock">true</field>
+</doc>
+
+<doc>
+  <field name="id">VDBDB1A16</field>
+  <field name="name">A-DATA V-Series 1GB 184-Pin DDR SDRAM Unbuffered DDR 400 (PC 3200) System Memory - OEM</field>
+  <field name="manu">A-DATA Technology Inc.</field>
+  <field name="cat">electronics</field>
+  <field name="cat">memory</field>
+  <field name="features">CAS latency 3,	 2.7v</field>
+  <!-- note: price is missing on this one -->
+  <field name="popularity">5</field>
+  <field name="inStock">true</field>
+
+</doc>
+
+
+
+</add>
+
diff --git a/example/exampledocs/monitor.xml b/example/exampledocs/monitor.xml
new file mode 100755
index 00000000000..dec40ebd652
--- /dev/null
+++ b/example/exampledocs/monitor.xml
@@ -0,0 +1,14 @@
+<add><doc>
+  <field name="id">3007WFP</field>
+  <field name="name">Dell Widescreen UltraSharp 3007WFP</field>
+  <field name="manu">Dell, Inc.</field>
+  <field name="cat">electronics</field>
+  <field name="cat">monitor</field>
+  <field name="features">30" TFT active matrix LCD, 2560 x 1600, .25mm dot pitch, 700:1 contrast</field>
+  <field name="includes">USB cable</field>
+  <field name="weight">401.6</field>
+  <field name="price">2199</field>
+  <field name="popularity">6</field>
+  <field name="inStock">true</field>
+</doc></add>
+
diff --git a/example/exampledocs/monitor2.xml b/example/exampledocs/monitor2.xml
new file mode 100755
index 00000000000..0d138067804
--- /dev/null
+++ b/example/exampledocs/monitor2.xml
@@ -0,0 +1,13 @@
+<add><doc>
+  <field name="id">VA902B</field>
+  <field name="name">ViewSonic VA902B - flat panel display - TFT - 19"</field>
+  <field name="manu">ViewSonic Corp.</field>
+  <field name="cat">electronics</field>
+  <field name="cat">monitor</field>
+  <field name="features">19" TFT active matrix LCD, 8ms response time, 1280 x 1024 native resolution</field>
+  <field name="weight">190.4</field>
+  <field name="price">279.95</field>
+  <field name="popularity">6</field>
+  <field name="inStock">true</field>
+</doc></add>
+
diff --git a/example/exampledocs/mp500.xml b/example/exampledocs/mp500.xml
new file mode 100755
index 00000000000..0d3ce51ef47
--- /dev/null
+++ b/example/exampledocs/mp500.xml
@@ -0,0 +1,22 @@
+<add><doc>
+  <field name="id">0579B002</field>
+  <field name="name">Canon PIXMA MP500 All-In-One Photo Printer</field>
+  <field name="manu">Canon Inc.</field>
+  <field name="cat">electronics</field>
+  <field name="cat">multifunction printer</field>
+  <field name="cat">printer</field>
+  <field name="cat">scanner</field>
+  <field name="cat">copier</field>
+  <field name="features">Multifunction ink-jet color photo printer</field>
+  <field name="features">Flatbed scanner, optical scan resolution of 1,200 x 2,400 dpi</field>
+  <field name="features">2.5" color LCD preview screen</field>
+  <field name="features">Duplex Copying</field>
+  <field name="features">Printing speed up to 29ppm black, 19ppm color</field>
+  <field name="features">Hi-Speed USB</field>
+  <field name="features">memory card: CompactFlash, Micro Drive, SmartMedia, Memory Stick, Memory Stick Pro, SD Card, and MultiMediaCard</field>
+  <field name="weight">352</field>
+  <field name="price">179.99</field>
+  <field name="popularity">6</field>
+  <field name="inStock">true</field>
+</doc></add>
+
diff --git a/example/exampledocs/post.sh b/example/exampledocs/post.sh
new file mode 100755
index 00000000000..3f947851f1d
--- /dev/null
+++ b/example/exampledocs/post.sh
@@ -0,0 +1,12 @@
+#!/bin/sh
+FILES=$*
+URL=http://localhost:8983/solr/update
+
+for f in $FILES; do
+  echo Posting file $f to $URL
+  curl $URL --data-binary @$f
+done
+
+#send the commit command to make sure all the changes are flushed and visible
+curl $URL --data-binary '<commit/>'
+
diff --git a/example/exampledocs/sd500.xml b/example/exampledocs/sd500.xml
new file mode 100755
index 00000000000..76864cba75d
--- /dev/null
+++ b/example/exampledocs/sd500.xml
@@ -0,0 +1,16 @@
+<add><doc>
+  <field name="id">9885A004</field>
+  <field name="name">Canon Powershot SD500</field>
+  <field name="manu">Canon Inc.</field>
+  <field name="cat">electronics</field>
+  <field name="cat">camera</field>
+  <field name="features">3x zoop, 7.1 megapixel Digital ELPH</field>
+  <field name="features">movie clips up to 640x480 @30 fps</field>
+  <field name="features">2.0" TFT LCD, 118,000 pixels</field>
+  <field name="features">built in flash, red-eye reduction</field>
+  <field name="includes">32MB SD card, USB cable, AV cable, battery</field>
+  <field name="weight">6.4</field>
+  <field name="price">329.95</field>
+  <field name="popularity">7</field>
+  <field name="inStock">true</field>
+</doc></add>
diff --git a/example/exampledocs/vidcard.xml b/example/exampledocs/vidcard.xml
new file mode 100755
index 00000000000..ab54381295b
--- /dev/null
+++ b/example/exampledocs/vidcard.xml
@@ -0,0 +1,35 @@
+<add>
+<doc>
+  <field name="id">EN7800GTX/2DHTV/256M</field>
+  <field name="name">ASUS Extreme N7800GTX/2DHTV (256 MB)</field>
+  <field name="manu">ASUS Computer Inc.</field>
+  <field name="cat">electronics</field>
+  <field name="cat">graphics card</field>
+  <field name="features">NVIDIA GeForce 7800 GTX GPU/VPU clocked at 486MHz</field>
+  <field name="features">256MB GDDR3 Memory clocked at 1.35GHz</field>
+  <field name="features">PCI Express x16</field>
+  <field name="features">Dual DVI connectors, HDTV out, video input</field>
+  <field name="features">OpenGL 2.0, DirectX 9.0</field>
+  <field name="weight">16</field>
+  <field name="price">479.95</field>
+  <field name="popularity">7</field>
+  <field name="inStock">false</field>
+</doc>
+  <!-- yes, you can add more than one document at a time -->
+<doc>
+  <field name="id">100-435805</field>
+  <field name="name">ATI Radeon X1900 XTX 512 MB PCIE Video Card</field>
+  <field name="manu">ATI Technologies</field>
+  <field name="cat">electronics</field>
+  <field name="cat">graphics card</field>
+  <field name="features">ATI RADEON X1900 GPU/VPU clocked at 650MHz</field>
+  <field name="features">512MB GDDR3 SDRAM clocked at 1.55GHz</field>
+  <field name="features">PCI Express x16</field>
+  <field name="features">dual DVI, HDTV, svideo, composite out</field>
+  <field name="features">OpenGL 2.0, DirectX 9.0</field>
+  <field name="weight">48</field>
+  <field name="price">649.99</field>
+  <field name="popularity">7</field>
+  <field name="inStock">false</field>
+</doc>
+</add>