rroonga 1.2.5-x86-mingw32 → 1.2.7-x86-mingw32

data/vendor/local/share/doc/groonga/source/suggest/correction.txt

@@ -0,0 +1,148 @@
+.. -*- rst -*-
+
+.. highlightlang:: none
+
+.. groonga-command
+.. % groonga-suggest-create-dataset /tmp/groonga-databases/correction query
+.. database: correction
+
+Correction
+==========
+
+This section describes about the following correction
+features:
+
+* How it works
+* How to use
+* How to learn
+
+How it works
+------------
+
+The correction feature uses three searches to compute corrected
+words:
+
+  1. Cooccurrence search against learned data.
+  2. Similar search against registered words. (optional)
+
+Cooccurrence search
+^^^^^^^^^^^^^^^^^^^
+
+Cooccurrence search can find registered words from user's
+wrong input. It uses user submit sequences that will be
+learned from query logs, access logs and so on.
+
+For example, there are the following user submissions:
+
++-------------------+---------------------------+
+|  query            |    time                   |
++===================+===========================+
+| serach (typo!)    | 2011-08-10T22:20:50+09:00 |
++-------------------+---------------------------+
+| search (fixed!)   | 2011-08-10T22:20:52+09:00 |
++-------------------+---------------------------+
+
+Groonga creates the following correction pair from the above
+submissions:
+
++----------+--------------------+
+|  input   |   corrected word   |
++==========+====================+
+|serach    |search              |
++----------+--------------------+
+
+Groonga treats continuous submissions within a minute as
+input correction by user. Not submitted user input sequence
+between two submissions isn't used as learned data for
+correction.
+
+If an user inputs "serach" and cooccurrence search returns
+"search" because "serach" is in input column and
+corresponding corrected word column value is "search".
+
+Similar search
+^^^^^^^^^^^^^^
+
+Similar search can find registered words that has one or
+more the same tokens as user input. TokenBigram tokenizer is
+used for tokenization because suggest dataset schema
+created by :doc:`/executables/groonga-suggest-create-dataset`
+uses TokenBigram tokenizer as the default tokenizer.
+
+For example, there is a registered query "search engine". An
+user can find "search engine" by "web search service",
+"sound engine" and so on. Because "search engine" and "web
+search engine" have the same token "search" and "search
+engine" and "sound engine" have the same token "engine".
+
+"search engine" is tokenized to "search" and "engine"
+tokens. (Groonga's TokenBigram tokenizer doesn't tokenize
+two characters for continuous alphabets and continuous
+digits for reducing search
+noise. TokenBigramSplitSymbolAlphaDigit tokenizer should be
+used to ensure tokenizing to two characters.) "web search
+service" is tokenized to "web", "search" and
+"service". "sound engine" is tokenized to "sound" and
+"engine".
+
+How to use
+----------
+
+.. groonga-command
+.. load --table event_query --each 'suggest_preparer(_id, type, item, sequence, time, pair_query)'
+.. [
+.. {"sequence": "1", "time": 1312950803.86057, "item": "s"},
+.. {"sequence": "1", "time": 1312950803.96857, "item": "sa"},
+.. {"sequence": "1", "time": 1312950804.26057, "item": "sae"},
+.. {"sequence": "1", "time": 1312950804.56057, "item": "saer"},
+.. {"sequence": "1", "time": 1312950804.76057, "item": "saerc"},
+.. {"sequence": "1", "time": 1312950805.76057, "item": "saerch", "type": "submit"},
+.. {"sequence": "1", "time": 1312950809.76057, "item": "serch"},
+.. {"sequence": "1", "time": 1312950810.86057, "item": "search", "type": "submit"}
+.. ]
+
+Groonga provides :doc:`/commands/suggest` command to use
+correction. `--type correct` option requests corrections.
+
+For example, here is an command to get correction results by
+"saerch":
+
+.. groonga-command
+.. include:: ../example/correction-1.log
+.. suggest --table item_query --column kana --types correction --frequency_threshold 1 --query saerch
+
+How it learns
+-------------
+
+Cooccurrence search uses learned data. They are based on
+query logs, access logs and so on. To create learned data,
+groonga needs user submit inputs with time stamp.
+
+For example, an user wants to search by "search" but the
+user has typo "saerch" before inputs the correct query. The
+user inputs the query with the following sequence:
+
+  1. 2011-08-10T13:33:23+09:00: s
+  2. 2011-08-10T13:33:23+09:00: sa
+  3. 2011-08-10T13:33:24+09:00: sae
+  4. 2011-08-10T13:33:24+09:00: saer
+  5. 2011-08-10T13:33:24+09:00: saerc
+  6. 2011-08-10T13:33:25+09:00: saerch (submit!)
+  7. 2011-08-10T13:33:29+09:00: serch (correcting...)
+  8. 2011-08-10T13:33:30+09:00: search (submit!)
+
+Groonga can be learned from the input sequence by the
+following command::
+
+  load --table event_query --each 'suggest_preparer(_id, type, item, sequence, time, pair_query)'
+  [
+  {"sequence": "1", "time": 1312950803.86057, "item": "s"},
+  {"sequence": "1", "time": 1312950803.96857, "item": "sa"},
+  {"sequence": "1", "time": 1312950804.26057, "item": "sae"},
+  {"sequence": "1", "time": 1312950804.56057, "item": "saer"},
+  {"sequence": "1", "time": 1312950804.76057, "item": "saerc"},
+  {"sequence": "1", "time": 1312950805.76057, "item": "saerch", "type": "submit"},
+  {"sequence": "1", "time": 1312950809.76057, "item": "serch"},
+  {"sequence": "1", "time": 1312950810.86057, "item": "search", "type": "submit"}
+  ]
+

data/vendor/local/share/doc/groonga/source/suggest/introduction.txt

@@ -0,0 +1,94 @@
+.. -*- rst -*-
+
+.. highlightlang:: none
+
+Introduction
+============
+
+The suggest feature in groonga provides the following features:
+
+* Completion
+* Correction
+* Suggestion
+
+Completion
+----------
+
+Completion helps user input. If user inputs a partial word,
+groonga can return complete words from registered
+words.
+
+For example, there are registered words:
+
+* "groonga"
+* "complete"
+* "correction"
+* "suggest"
+
+An user inputs "co" and groonga returns "complete" and
+"correction" because they starts with "co".
+
+An user inputs "sug" and groonga returns "suggest" because
+"suggest" starts with "sug".
+
+An user inputs "ab" and groonga returns nothing because no
+word starts with "ab".
+
+Correction
+----------
+
+Correction also helps user input. If user inputs a wrong
+word, groonga can return correct words from registered
+correction pairs.
+
+For example, there are registered correction pairs:
+
++------------+--------------+
+| wrong word | correct word |
++============+==============+
+| grroonga   | groonga      |
+| gronga     | groonga      |
+| gronnga    | groonga      |
++------------+--------------+
+
+An user inputs "gronga" and groonga returns "groonga" because
+"gronga" is in wrong word and corresponding correct word is
+"groonga".
+
+An user inputs "roonga" and groonga returns nothing because
+"roonga" isn't in wrong word.
+
+Suggestion
+----------
+
+Suggestion helps that user filters many found documents. If
+user inputs a query, groonga can return new queries that has
+more additional keywords from registered related query
+pairs.
+
+For example, there are registered related query pairs:
+
++----------------------------+--------------------------+
+|          keyword           |      related query       |
++============================+==========================+
+| groonga                    | groonga search engine    |
++----------------------------+--------------------------+
+| search                     | Google search            |
++----------------------------+--------------------------+
+| speed                      | groonga speed            |
++----------------------------+--------------------------+
+
+An user inputs "groonga" and groonga returns "groonga search
+engine" because "groonga" is in keyword column and related
+query column is "groonga search engine".
+
+An user inputs "MySQL" and groonga returns nothing because
+"MySQL" isn't in keyword column values.
+
+Learning
+--------
+
+The suggest feature requires registered data before using
+the feature. Those data can be registered from user inputs.
+Gronnga-suggest-httpd and groonga-suggest-learner commands
+are provided for the propose.

data/vendor/local/share/doc/groonga/source/suggest/suggestion.txt

@@ -0,0 +1,115 @@
+.. -*- rst -*-
+
+.. highlightlang:: none
+
+.. groonga-command
+.. % groonga-suggest-create-dataset /tmp/groonga-databases/suggestion query
+.. database: suggestion
+
+Suggestion
+==========
+
+This section describes about the following completion
+features:
+
+* How it works
+* How to use
+* How to learn
+
+How it works
+------------
+
+The suggestion feature uses a search to compute suggested
+words:
+
+  1. Cooccurrence search against learned data.
+
+Cooccurrence search
+^^^^^^^^^^^^^^^^^^^
+
+Cooccurrence search can find related words from user's
+input. It uses user submissions that will be learned
+from query logs, access logs and so on.
+
+For example, there are the following user submissions:
+
++----------------------+
+|  query               |
++======================+
+| search engine        |
++----------------------+
+| web search realtime  |
++----------------------+
+
+Groonga creates the following suggestion pairs:
+
++----------+------------------------------------+
+|  input   |          suggested words           |
++==========+====================================+
+|search    |search engine                       |
++----------+------------------------------------+
+|engine    |search engine                       |
++----------+------------------------------------+
+|web       |web search realtime                 |
++----------+------------------------------------+
+|search    |web search realtime                 |
++----------+------------------------------------+
+|realtime  |web search realtime                 |
++----------+------------------------------------+
+
+Those pairs are created by the following steps:
+
+  1. Tokenizes user input query by TokenDelimit tokenizer
+     that uses a space as token delimiter. (e.g. "search
+     engine" is tokenized to two tokens "search" and
+     "engine".)
+  2. Creates a pair that is consists of a token and original
+     query for each token.
+
+If an user inputs "search" and cooccurrence search returns
+"search engine" and "web search realtime" because "search" is
+in two input columns and corresponding suggested word
+columns have "search engine" and "web search realtime".
+
+How to use
+----------
+
+.. groonga-command
+.. load --table event_query --each 'suggest_preparer(_id, type, item, sequence, time, pair_query)'
+.. [
+.. {"sequence": "1", "time": 1312950803.86057, "item": "search engine", "type": "submit"},
+.. {"sequence": "1", "time": 1312950808.86057, "item": "web search realtime", "type": "submit"}
+.. ]
+
+Groonga provides :doc:`/commands/suggest` command to use
+suggestion. `--type suggest` option requests suggestion
+
+For example, here is an command to get suggestion results by
+"search":
+
+.. groonga-command
+.. include:: ../example/suggestion-1.log
+.. suggest --table item_query --column kana --types suggest --frequency_threshold 1 --query search
+
+How it learns
+-------------
+
+Cooccurrence search uses learned data. They are based on
+query logs, access logs and so on. To create learned data,
+groonga needs user input sequence with time stamp and user
+submit input with time stamp.
+
+For example, an user wants to search by "engine". The user
+inputs the query with the following sequence:
+
+  1. 2011-08-10T13:33:23+09:00: search engine (submit)
+  2. 2011-08-10T13:33:28+09:00: web search realtime (submit)
+
+Groonga can be learned from the submissions by the
+following command::
+
+  load --table event_query --each 'suggest_preparer(_id, type, item, sequence, time, pair_query)'
+  [
+  {"sequence": "1", "time": 1312950803.86057, "item": "search engine", "type": "submit"},
+  {"sequence": "1", "time": 1312950808.86057, "item": "web search realtime", "type": "submit"}
+  ]

data/vendor/local/share/doc/groonga/source/suggest/tutorial.txt

@@ -0,0 +1,8 @@
+.. -*- rst -*-
+
+.. highlightlang:: none
+
+Tutorial
+========
+
+TODO...

data/vendor/local/share/doc/groonga/source/suggest.txt

@@ -0,0 +1,22 @@
+.. -*- rst -*-
+
+.. highlightlang:: none
+
+Suggest
+=======
+
+.. note::
+
+   The suggest feature specification isn't stable. The
+   specification may be changed.
+
+Groonga has the suggest feature. This section describes how to use it and how it works.
+
+.. toctree::
+   :maxdepth: 2
+
+   suggest/introduction
+   suggest/tutorial
+   suggest/completion
+   suggest/correction
+   suggest/suggestion

data/vendor/local/share/doc/groonga/source/tutorial/tutorial01.txt

@@ -3,6 +3,7 @@
 .. highlightlang:: none
 
 .. groonga-command
+.. database: tutorial
 .. table_remove Site
 .. table_remove Terms
 
@@ -73,7 +74,7 @@ groonga実行ファイルやgroongaサーバを介して様々なコマンドを
 
 書式2において、空白や、記号「"'()\」のうちいずれかを含む値を指定したい場合は、シングルクォート(')かダブルクォート(")で値を囲みます。
 
-詳しくは、 :doc:`/execfile` のコマンドの項を参考にしてください。
+詳しくは、 :doc:`/executables/groonga` のコマンドの項を参考にしてください。
 
 主なコマンド
 ------------

data/vendor/local/share/doc/groonga/source/update_execution_example.py

@@ -5,16 +5,32 @@ from subprocess import *
 from select import select
 from sys import argv,stdout
 import os
+import os.path
+import shutil
 
-GROONGA_PATH = os.environ.get("GROONGA")
-if GROONGA_PATH is None:
-  GROONGA_PATH = "groonga"
-DB_PATH = "/tmp/example.db"
+DB_DIRECTORY = "/tmp/groonga-databases"
 
-os.system('rm -rf %s*' % DB_PATH)
-ioobj = Popen([GROONGA_PATH, '-n', DB_PATH], stdin = PIPE, stdout = PIPE)
-ioin  = ioobj.stdin
-ioout = ioobj.stdout
+shutil.rmtree(DB_DIRECTORY, ignore_errors=True)
+os.makedirs(DB_DIRECTORY)
+
+groonga_process = None
+def close_groonga():
+  global groonga_process
+  if groonga_process:
+    groonga_process.stdin.close()
+    groonga_process.stdout.close()
+    groonga_process = None
+    print '###<<< database: close'
+
+def reconnect(name):
+  global groonga_process
+  close_groonga()
+  db_path = os.path.join(DB_DIRECTORY, name)
+  if os.path.exists(db_path):
+    groonga_process = Popen(["groonga", db_path], stdin=PIPE, stdout=PIPE)
+  else:
+    groonga_process = Popen(["groonga", "-n", db_path], stdin=PIPE, stdout=PIPE)
+  print '###>>> database: open <%s>' % db_path
 
 fout = None
 
@@ -22,14 +38,14 @@ def execmd(cmd, fout):
   a = '> ' + cmd + "\n"
   stdout.write(a)
   stdout.flush()
-  ioin.write(cmd + "\n")
-  ioin.flush()
+  groonga_process.stdin.write(cmd + "\n")
+  groonga_process.stdin.flush()
   if fout:
     fout.write(a + "  ")
   while True:
-    out = select([ioout], [], [], 0.2)
+    out = select([groonga_process.stdout], [], [], 0.2)
     if len(out[0]):
-      a = ioout.read(1)
+      a = groonga_process.stdout.read(1)
       if a != None:
         stdout.write(a)
         if fout:
@@ -63,7 +79,10 @@ def readfile(fname, outflag):
       fout = None
       while len(dat):
         cmd = dat.pop(0)
-        if cmd.startswith('.. include:: '):
+        if cmd.startswith('.. database:'):
+          database_name = cmd[cmd.index(":")+1:].strip()
+          reconnect(database_name)
+        elif cmd.startswith('.. include:: '):
           a = rootdir + cmd[13:]
           if outflag == 0:
             dir_name = os.path.dirname(a)
@@ -71,7 +90,13 @@ def readfile(fname, outflag):
               os.makedirs(dir_name)
             fout = open(a, 'w')
             print '### write start : ' + a
-            fout.write("実行例 ::\n\n  ")
+            fout.write("Execution example::\n\n  ")
+        elif cmd.startswith('.. % '):
+          a = cmd[5:]
+          if fout:
+            fout.write(a + "\n  ")
+          print a
+          os.system(a)
         elif cmd.startswith('.. .. '):
           a = cmd[6:]
           if fout:
@@ -97,11 +122,13 @@ def readfile(fname, outflag):
       readfile(a, outflag + 1)
       print '###<<< include end'
 
-
-if len(argv) > 1:
-  readfile(argv[1], 0)
+entry_point = "./"
+if len(argv) == 2:
+  entry_point = argv[1]
+if os.path.isfile(entry_point):
+  readfile(entry_point, 0)
 else:
-  for root, dirs, files in os.walk('./'):
+  for root, dirs, files in os.walk(entry_point):
     for fname in files:
       if fname.lower().endswith('.txt'):
         b = os.path.join(root, fname)
@@ -110,6 +137,5 @@ else:
 
 if fout:
   fout.close()
-ioin.close()
-ioout.close()
+close_groonga()
 

data/vendor/local/share/license/groonga/AUTHORS

@@ -0,0 +1,17 @@
+Primary authors:
+Daijiro MORI <morita at razil. jp>
+Tasuku SUENAGA <a at razil. jp>
+Yutaro Shimamura <yu at razil. jp>
+Kouhei Sutou <kou at cozmixng. org>
+Kazuho Oku <kazuhooku at gmail. com>
+Moriyoshi Koizumi <moriyoshi at gmail. com>
+
+Patches and modules from:
+Daisuke Maki <dmaki at cpan. org>
+Kazuhiro Osawa <ko at yappo. ne. jp>
+Hiroyuki OYAMA <oyama at module. jp>
+Nguyen Anh Phu <phuna at users. sourceforge. net>
+Hideyuki KUROSU <hideyuki. kurosu at gmail. com>
+Takuo Kitame <kitame at valinux. co. jp>
+Yoshihiro Oyama <yos-o at smilemark. com>
+cZfSunOs.U <sunos at saita. ma>