Merge branch 'PGPRO_shared_ispell' into PGPRO9_5

vbwagner · vbwagner · commit cfd0ba56e01c · 2016-03-22T13:52:29.000+03:00
diff --git a/contrib/hunspell_nl_nl/dict/nl_nl.dict b/contrib/hunspell_nl_nl/dict/nl_nl.dict
@@ -137886,10 +137886,6 @@ procureursgeneraal/Fw
 in-vitro/CeCxC1C2C3C4C5
 waterkering/CAZbC0
 huisvester/CxCcC0
-Oost\/Watergraafsmeer
-km\/h
-km\/u
-m\/s
 Palmzondag
 palmzondag/Fw
 ballingsoort/Fw
diff --git a/contrib/shared_ispell/README.md b/contrib/shared_ispell/README.md
@@ -133,3 +133,20 @@ use this prepared data).
     db=# SELECT shared_ispell_reset();
 
 That's all for now ...
+
+Changes from original version
+-----------------------------
+The original version of this module located in the Tomas Vondra's
+[GitHub](https://github.com/tvondra/shared_ispell). That version does not handle
+affixes that require full regular expressions (regex_t, implemented in regex.h).
+
+This version of the module can handle that affixes with full regular
+exressions. To handle it the module loads and stores affix files in each
+sessions. The affix list is tiny and takes a little time and memory to parse.
+Actually this is Tomas
+[idea](http://www.postgresql.org/message-id/56A5F3D5.9030702@2ndquadrant.com),
+but there is not related code in the GitHub.
+
+Author
+------
+Tomas Vondra [GitHub](https://github.com/tvondra)
diff --git a/contrib/shared_ispell/src/shared_ispell.c b/contrib/shared_ispell/src/shared_ispell.c
@@ -264,6 +264,9 @@ clean_dict_affix(IspellDict *dict)
 	dict->nAffixData = 0;
 
 	dict->CompoundAffix = NULL;
+	dict->CompoundAffixFlags = NULL;
+	dict->nCompoundAffixFlag = 0;
+	dict->mCompoundAffixFlag = 0;
 
 	dict->avail = 0;
 }
@@ -315,7 +318,13 @@ init_shared_dict(DictInfo *info, char *dictFile, char *affFile, char *stopFile)
 		NIImportDictionary(dict, get_tsearch_config_filename(dictFile, "dict"));
 
 		dict->usecompound = info->dict.usecompound;
-		memcpy(dict->flagval, &(info->dict.flagval), 65000);
+
+		dict->nCompoundAffixFlag = dict->mCompoundAffixFlag =
+			info->dict.nCompoundAffixFlag;
+		dict->CompoundAffixFlags = (CompoundAffixFlag *) palloc0(
+			dict->nCompoundAffixFlag * sizeof(CompoundAffixFlag));
+		memcpy(dict->CompoundAffixFlags, info->dict.CompoundAffixFlags,
+			   dict->nCompoundAffixFlag * sizeof(CompoundAffixFlag));
 
 		/*
 		 * If affix->useFlagAliases == true then AffixData is generated
diff --git a/src/backend/tsearch/Makefile b/src/backend/tsearch/Makefile
@@ -14,10 +14,15 @@ include $(top_builddir)/src/Makefile.global
 
 DICTDIR=tsearch_data
 
-DICTFILES=dicts/synonym_sample.syn dicts/thesaurus_sample.ths \
-	dicts/hunspell_sample.affix dicts/ispell_sample.affix dicts/ispell_sample.dict \
-	dicts/hunspell_sample_long.affix dicts/hunspell_sample_long.dict \
-	dicts/hunspell_sample_num.affix dicts/hunspell_sample_num.dict
+# List of dictionaries files
+DICTFILES=synonym_sample.syn thesaurus_sample.ths \
+	hunspell_sample.affix \
+	ispell_sample.affix ispell_sample.dict \
+	hunspell_sample_long.affix hunspell_sample_long.dict \
+	hunspell_sample_num.affix hunspell_sample_num.dict
+
+# Local paths to dictionaries files
+DICTFILES_PATH=$(addprefix dicts/,$(DICTFILES))
 
 OBJS = ts_locale.o ts_parse.o wparser.o wparser_def.o dict.o \
 	dict_simple.o dict_synonym.o dict_thesaurus.o \
@@ -27,8 +32,8 @@ OBJS = ts_locale.o ts_parse.o wparser.o wparser_def.o dict.o \
 include $(top_srcdir)/src/backend/common.mk
 
 .PHONY: install-data
-install-data: $(DICTFILES) installdirs
-	$(INSTALL_DATA) $(addprefix $(srcdir)/,$(DICTFILES)) '$(DESTDIR)$(datadir)/$(DICTDIR)/'
+install-data: $(DICTFILES_PATH) installdirs
+	$(INSTALL_DATA) $(addprefix $(srcdir)/,$(DICTFILES_PATH)) '$(DESTDIR)$(datadir)/$(DICTDIR)/'
 
 installdirs:
 	$(MKDIR_P) '$(DESTDIR)$(datadir)' '$(DESTDIR)$(datadir)/$(DICTDIR)'
diff --git a/src/backend/tsearch/dicts/hunspell_sample.affix b/src/backend/tsearch/dicts/hunspell_sample.affix
@@ -21,4 +21,3 @@ SFX A   Y	IES	[^AEIOU]Y
 
 SFX \ N 1
 SFX \   0	Y/L	[^Y]
-
diff --git a/src/backend/tsearch/dicts/hunspell_sample_long.affix b/src/backend/tsearch/dicts/hunspell_sample_long.affix
@@ -32,4 +32,3 @@ SFX sA   Y	IES	[^AEIOU]Y
 
 SFX s\ N 1
 SFX s\   0	Y/2	[^Y]
-
diff --git a/src/backend/tsearch/dicts/hunspell_sample_num.affix b/src/backend/tsearch/dicts/hunspell_sample_num.affix
@@ -23,4 +23,3 @@ SFX 304   Y	IES	[^AEIOU]Y
 
 SFX 305 N 1
 SFX 305   0	Y/102	[^Y]
-
diff --git a/src/backend/tsearch/spell.c b/src/backend/tsearch/spell.c
diff --git a/src/include/tsearch/dicts/spell.h b/src/include/tsearch/dicts/spell.h

Original file line number	Diff line number	Diff line change
`@@ -21,4 +21,3 @@ SFX A Y IES [^AEIOU]Y`
`21`	`21`
`22`	`22`	`SFX \ N 1`
`23`	`23`	`SFX \ 0 Y/L [^Y]`
`24`		`-`
Original file line number	Diff line number	Diff line change
`@@ -32,4 +32,3 @@ SFX sA Y IES [^AEIOU]Y`
`32`	`32`
`33`	`33`	`SFX s\ N 1`
`34`	`34`	`SFX s\ 0 Y/2 [^Y]`
`35`		`-`
Original file line number	Diff line number	Diff line change
`@@ -23,4 +23,3 @@ SFX 304 Y IES [^AEIOU]Y`
`23`	`23`
`24`	`24`	`SFX 305 N 1`
`25`	`25`	`SFX 305 0 Y/102 [^Y]`
`26`		`-`