Skip to content

Commit e9bbb94

Browse files
martindholmesmartindholmes
committed
Initial work on issue #322 (moving stopwords and dictionary files). This will require a further update to the conversion script once merged into dev.
1 parent 05e9c6c commit e9bbb94

File tree

9 files changed

+112
-100
lines changed

9 files changed

+112
-100
lines changed

‎config_documentation.xml

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -4,8 +4,8 @@
44
<params>
55
<searchPage file="docs/index.html"/>
66
<index recurse="false"/>
7-
<stopwords file="xsl/english_stopwords.txt"/>
8-
<dictionary file="xsl/english_words.txt"/>
7+
<stopwords file="stopwords/stopwords_en.txt"/>
8+
<dictionary file="dicts/words_en.txt"/>
99
<scoringAlgorithm name="raw"/>
1010
<stemmer dir="stemmers/en"/>
1111
<tokenizer minWordLength="2"/>

‎xsl/english_words.txt renamed to ‎dicts/words_en.txt

File renamed without changes.

‎xsl/french_words.txt renamed to ‎dicts/words_fr.txt

File renamed without changes.

‎docs/staticSearch.html

Lines changed: 93 additions & 90 deletions
Large diffs are not rendered by default.

‎schema/staticSearch.odd

Lines changed: 12 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1250,7 +1250,7 @@
12501250

12511251
</div>
12521252

1253-
<div xml:id="newSinceVersion1">
1253+
<div xml:id="newSinceLastVersion">
12541254
<head>What's new since version 1.4?</head>
12551255
<list>
12561256
<item>Level: Intermediate</item>
@@ -1260,6 +1260,15 @@
12601260
<head>Changes in version 2.0</head>
12611261

12621262
<list>
1263+
<item>The included dictionaries and stopwords lists for English and
1264+
French have been moved from the <ident>xsl</ident> folder to new locations:
1265+
<ident>dicts/words_en.txt</ident>, <ident>dicts/words_fr.txt</ident>,
1266+
<ident>stopwords/stopwords_en.txt</ident>, and
1267+
<ident>stopwords/stopwords_fr.txt</ident>. This is purely for
1268+
housekeeping purposes. If you have a configuration file which points at
1269+
one of these files in the old location, you will need to update that
1270+
file.</item>
1271+
12631272
<item>Five JavaScript CustomEvents are now dispatched by the StaticSearch object, to better
12641273
enable programmers to write JavaScript code which interacts with the search page. See
12651274
<ref target="#programming">Programming with staticSearch</ref> for more details.</item>
@@ -1578,7 +1587,7 @@
15781587
<attDef ident="file" mode="change">
15791588
<gloss>The path (relative to the config file) to a text file
15801589
containing a list of words to be ignored by the indexer (one word per line).</gloss>
1581-
<defaultVal>xsl/english_stopwords.txt</defaultVal>
1590+
<defaultVal>stopwords/stopwords_en.txt</defaultVal>
15821591
</attDef>
15831592
</attList>
15841593
<remarks>
@@ -1613,7 +1622,7 @@
16131622
<attList>
16141623
<attDef ident="file" mode="change">
16151624
<gloss>The relative path (from the config file) to a dictionary file (one word per line).</gloss>
1616-
<defaultVal>xsl/english_words.txt</defaultVal>
1625+
<defaultVal>dicts/words_en.txt</defaultVal>
16171626
</attDef>
16181627
</attList>
16191628
<remarks>

‎schema/staticSearch.rng

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@
55
xmlns:xlink="http://www.w3.org/1999/xlink"
66
datatypeLibrary="http://www.w3.org/2001/XMLSchema-datatypes"
77
ns="http://hcmc.uvic.ca/ns/staticSearch"><!--
8-
Schema generated from ODD source 2025-02-23T18:18:59Z. 2019-2025.
8+
Schema generated from ODD source 2025-02-23T18:31:59Z. 2019-2025.
99
TEI Edition: P5 Version 4.9.0. Last updated on 24th January 2025, revision f73186978
1010
TEI Edition Location: https://www.tei-c.org/Vault/P5/4.9.0/
1111
@@ -32,7 +32,7 @@ TEI Edition Location: https://www.tei-c.org/Vault/P5/4.9.0/
3232
<ns xmlns="http://purl.oclc.org/dsdl/schematron"
3333
prefix="xh"
3434
uri="http://www.w3.org/1999/xhtml"/>
35-
<pattern xmlns="http://purl.oclc.org/dsdl/schematron" id="d9e3384-constraint">
35+
<pattern xmlns="http://purl.oclc.org/dsdl/schematron" id="d9e3397-constraint">
3636
<rule context="xh:span">
3737
<report test="descendant::*[not(namespace-uri(.) = ('http://www.w3.org/1999/xhtml', 'http://www.tei-c.org/ns/1.0'))]">span descendants must be in the
3838
namespaces
@@ -153,7 +153,7 @@ TEI Edition Location: https://www.tei-c.org/Vault/P5/4.9.0/
153153
<empty/>
154154
<attribute xmlns:a="http://relaxng.org/ns/compatibility/annotations/1.0"
155155
name="file"
156-
a:defaultValue="xsl/english_stopwords.txt">
156+
a:defaultValue="stopwords/stopwords_en.txt">
157157
<a:documentation>(The path (relative to the config file) to a text file containing a list of words to be ignored by the indexer (one word per line).) </a:documentation>
158158
<data type="anyURI"/>
159159
</attribute>
@@ -166,7 +166,7 @@ TEI Edition Location: https://www.tei-c.org/Vault/P5/4.9.0/
166166
<empty/>
167167
<attribute xmlns:a="http://relaxng.org/ns/compatibility/annotations/1.0"
168168
name="file"
169-
a:defaultValue="xsl/english_words.txt">
169+
a:defaultValue="dicts/words_en.txt">
170170
<a:documentation>(The relative path (from the config file) to a dictionary file (one word per line).) </a:documentation>
171171
<data type="anyURI"/>
172172
</attribute>

‎schema/staticSearch.sch

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -82,7 +82,7 @@
8282
xmlns:tei="http://www.tei-c.org/ns/1.0"
8383
xmlns:teix="http://www.tei-c.org/ns/Examples"
8484
xmlns:xlink="http://www.w3.org/1999/xlink"
85-
id="d9e3384-constraint">
85+
id="d9e3397-constraint">
8686
<rule context="xh:span">
8787
<report test="descendant::*[not(namespace-uri(.) = ('http://www.w3.org/1999/xhtml', 'http://www.tei-c.org/ns/1.0'))]">span descendants must be in the
8888
namespaces

‎xsl/english_stopwords.txt renamed to ‎stopwords/stopwords_en.txt

File renamed without changes.

‎xsl/french_stopwords.txt renamed to ‎stopwords/stopwords_fr.txt

File renamed without changes.

0 commit comments

Comments
 (0)