From e67f3cbcc8ebc79e343459fa5aba9ed3e3cbe990 Mon Sep 17 00:00:00 2001 From: Adam Dickmeiss Date: Mon, 12 Nov 2007 11:13:05 +0000 Subject: [PATCH] Added yaz-icu man page --- doc/Makefile.am | 10 +- doc/yaz-icu-man.xml | 257 +++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 264 insertions(+), 3 deletions(-) create mode 100644 doc/yaz-icu-man.xml diff --git a/doc/Makefile.am b/doc/Makefile.am index 76a2fac..6b54e5b 100644 --- a/doc/Makefile.am +++ b/doc/Makefile.am @@ -1,4 +1,4 @@ -## $Id: Makefile.am,v 1.83 2007-07-10 09:42:46 adam Exp $ +## $Id: Makefile.am,v 1.84 2007-11-12 11:13:05 adam Exp $ SUBDIRS = common @@ -13,11 +13,12 @@ HTMLFILES = index.html MANFILES=yaz-client.1 yaz-ztest.8 \ yaz-config.8 yaz.7 zoomsh.1 yaz-asncomp.1 \ - yaz-marcdump.1 yaz-iconv.1 yaz-log.7 yaz-illclient.1 + yaz-marcdump.1 yaz-iconv.1 yaz-log.7 \ + yaz-illclient.1 yaz-icu.1 REFFILES=yaz-client-man.xml yaz-ztest-man.xml yaz-config-man.xml \ yaz-man.xml zoomsh-man.xml yaz-asncomp-man.xml \ yaz-marcdump-man.xml yaz-iconv-man.xml yaz-log-man.xml \ - yaz-illclient-man.xml + yaz-illclient-man.xml yaz-icu-man.xml SUPPORTFILES=entities.ent apilayer.obj local.ent.in @@ -60,6 +61,9 @@ yaz-illclient.1: yaz-illclient-man.xml yaz-log.7: yaz-log-man.xml $(MAN_COMPILE) $(srcdir)/yaz-log-man.xml +yaz-icu.1: yaz-icu-man.xml + $(MAN_COMPILE) $(srcdir)/yaz-icu-man.xml + $(HTMLFILES): $(XMLFILES) rm -f *.html $(HTML_COMPILE) $(srcdir)/yaz.xml diff --git a/doc/yaz-icu-man.xml b/doc/yaz-icu-man.xml new file mode 100644 index 0000000..90d78c6 --- /dev/null +++ b/doc/yaz-icu-man.xml @@ -0,0 +1,257 @@ + + %local; + + %entities; + + %idcommon; +]> + + + + YAZ + &version; + + + + yaz-icu + 1 + + + + yaz-icu + YAZ ICU utility + + + + + yaz-icu + commands + -c config + -p opt + -x + + + + DESCRIPTION + + yaz-icu is utility which demonstrates + the ICU chain module of yaz. (yaz/icu.h). + + + + OPTIONS + + + -c config + + Specifies the file containing ICU chain configuration + which is XML based. + + + + + -p type + + Specifies extra information to be printed about the ICU system. + If type is c + then ICU converters are printed. + If type is l + available locates are printed. + If type is t + available transliterators are printed. + + + + + -x config + + Specifies that output should be XML based rather than + "text" based. + + + + + + ICU chain configuration + + The ICU chain configuration speicifies one or more rules to convert + text data into tokens. The configuration format is XML based. + + + The toplevel element must be named icu_chain. + The icu_chain element has one required attribute + locale which specifies the ICU locale to be used + in the conversion steps. + + + The icu_chain element must include elements where + each element specifies a conversion step. The conversion is performed + in the order in which the conversion steps are specified. + Each conversion element takes one attribute: rule + which serves as argument to the conversion step. + + + The following conversion elements are available: + + + + casemap + + Converts case and rule specifies how: + + + + l + + Lowercase using ICU function u_strToLower. + + + + + u + + Upper case using ICU function u_strToUpper. + + + + + t + + To title using UCU function u_strToTitle. + + + + + f + + Fold case using ICU function u_strFoldCase. + + + + + + + + + display + + This is a meta step which specifies that a term/token is to + be displayed. This term is retrieved in an application + using function icu_chain_token_display (yaz/icu.h). + + + + + transform + + Specifies an ICU transform rule. The rule attribute is the + custom transformation rule to be used. This is a text based format + which is offered by the ICU transform system. See + ICU Transforms for + more information. + + + + + tokenize + + Breaks / tokenizes a string into components using + ICU functions ubrk_open, ubrk_setText, .. . The rule is + one of: + + + l + + Line. ICU: UBRK_LINE. + + + + + s + + Sentence. ICU: UBRK_SENTENCE. + + + + + w + + Word. ICU: UBRK_WORD. + + + + + c + + Character. ICU: UBRK_CHARACTER. + + + + + t + + Title. ICU: UBRK_TITLE. + + + + + + + + + + + + EXAMPLES + + The following command analyzes text in file text + using ICU chain configuration chain.xml: + + cat text | yaz-icu -c chain.xml + + The chain.xml might look as follows: + + + + + + + +]]> + + + + SEE ALSO + + + yaz + 7 + + + + ICU Home + + + ICU Transforms + + + + + -- 1.7.10.4