From d5bed6716c8868ee4fd8f764724d58aaa9917acd Mon Sep 17 00:00:00 2001
From: Fridolin Somers <fridolin.somers@biblibre.com>
Date: Fri, 10 Oct 2014 15:06:45 +0200
Subject: [PATCH] Bug 13064 - Indexing problem with ICU on control characters

The ICU configuration files contains a rule to remove control characters :
  <transform rule="[:Control:] Any-Remove"/>
This rule is before tokenization.

The problem is that "[:Control:]" regex contains line feed, carriage return and tab. See http://www.regular-expressions.info/posixbrackets.html.
So when several lines are indexed, last word of line is joined with first line of next line. Thoses words are then not searchable.

For example :
  First line
  Second line
This will become "First lineSecond line", tokenized as "First", "lineSecond" and "line".

Test plan :
- Use ICU in Zebra configuration
- Choose an indexed field, like 300$a
- Create a new record
- Enter several lines in choosen field, like :
  First line
  Second line
- Index this record
=> Without patch the search on "Second" does not return the record
=> With patch the search on "Second" returns the record
- Same tests with tab and carriage return instead of line feed

Signed-off-by: Chris Cormack <chris@bigballofwax.co.nz>
---
 etc/zebradb/etc/phrases-icu.xml | 3 ++-
 etc/zebradb/etc/words-icu.xml   | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/etc/zebradb/etc/phrases-icu.xml b/etc/zebradb/etc/phrases-icu.xml
index b27b06a..076c5ac 100644
--- a/etc/zebradb/etc/phrases-icu.xml
+++ b/etc/zebradb/etc/phrases-icu.xml
@@ -1,5 +1,6 @@
 <icu_chain locale="">
-  <transform rule="[:Control:] Any-Remove"/>
+  <!-- Remove control characters except \t\n\r -->
+  <transform rule="[\x00-\x08\x0B\x0C\x0E-\x1F\x7F] Any-Remove"/>
   <tokenize rule="l"/>
   <transform rule="[:Punctuation:] Remove"/>
   <transform rule="NFD"/>
diff --git a/etc/zebradb/etc/words-icu.xml b/etc/zebradb/etc/words-icu.xml
index 38af51f..57498cb 100644
--- a/etc/zebradb/etc/words-icu.xml
+++ b/etc/zebradb/etc/words-icu.xml
@@ -1,7 +1,8 @@
 <icu_chain locale="">
   <transliterate rule="\'>\ "/>
   <transliterate rule="[:Number:] { '-' > '' "/>
-  <transform rule="[:Control:] Any-Remove"/>
+  <!-- Remove control characters except \t\n\r -->
+  <transform rule="[\x00-\x08\x0B\x0C\x0E-\x1F\x7F] Any-Remove"/>
   <tokenize rule="l"/>
   <transform rule="[[:WhiteSpace:][:Punctuation:]] Remove"/>
   <transform rule="NFD"/>
-- 
1.9.1