This is an automated email from the ASF dual-hosted git repository.
ggregory pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/commons-codec.git
The following commit(s) were added to refs/heads/master by this push:
new 489a3ca6 Precompile regular expressions in
Lang.loadFromResource(String, Languages)
489a3ca6 is described below
commit 489a3ca6b82c9839ffa4b51a5999a06887acd4e1
Author: Gary Gregory <garydgreg...@gmail.com>
AuthorDate: Mon May 19 10:33:18 2025 -0400
Precompile regular expressions in Lang.loadFromResource(String,
Languages)
- Precompile regular expressions in PhoneticEngine.encode(String,
LanguageSet)
- Precompile regular expressions in
org.apache.commons.codec.language.bm.Rule.parse*(*)
---
src/changes/changes.xml | 7 +++++--
src/main/java/org/apache/commons/codec/language/bm/Lang.java | 6 ++++--
.../org/apache/commons/codec/language/bm/PhoneticEngine.java | 7 +++++--
.../apache/commons/codec/language/bm/ResourceConstants.java | 4 ++++
src/main/java/org/apache/commons/codec/language/bm/Rule.java | 10 +++++++---
5 files changed, 25 insertions(+), 9 deletions(-)
diff --git a/src/changes/changes.xml b/src/changes/changes.xml
index e8854a9e..eea6bb2a 100644
--- a/src/changes/changes.xml
+++ b/src/changes/changes.xml
@@ -48,8 +48,11 @@ The <action> type attribute can be add,update,fix,remove.
<action type="fix" dev="ggregory" due-to="Gary Gregory">Remove -nouses
directive from maven-bundle-plugin. OSGi package imports now state 'uses'
definitions for package imports, this doesn't affect JPMS (from
org.apache.commons:commons-parent:80).</action>
<action type="fix" dev="ggregory" due-to="Gary Gregory">Refactor
DigestUtils.updateDigest(MessageDigest, File) to use NIO.</action>
<action type="fix" dev="ggregory" due-to="Gary Gregory"
issue="CODEC-328" >Clarify Javadoc for
org.apache.commons.codec.digest.UnixCrypt.crypt(byte[],String).</action>
- <action type="fix" dev="ggregory" due-to="Gary Gregory">Precompile and
resuse x3 regular expression in DaitchMokotoffSoundex.Rule.</action>
- <action type="fix" dev="ggregory" due-to="Gary Gregory">Precompile and
resuse regular expressions in DaitchMokotoffSoundex.parseRules(Scanner, String,
Map, Map).</action>
+ <action type="fix" dev="ggregory" due-to="Gary Gregory">Precompile
regular expressions in DaitchMokotoffSoundex.Rule.</action>
+ <action type="fix" dev="ggregory" due-to="Gary Gregory">Precompile
regular expressions in DaitchMokotoffSoundex.parseRules(Scanner, String, Map,
Map).</action>
+ <action type="fix" dev="ggregory" due-to="Gary Gregory">Precompile
regular expressions in Lang.loadFromResource(String, Languages).</action>
+ <action type="fix" dev="ggregory" due-to="Gary Gregory">Precompile
regular expressions in PhoneticEngine.encode(String, LanguageSet).</action>
+ <action type="fix" dev="ggregory" due-to="Gary Gregory">Precompile
regular expressions in
org.apache.commons.codec.language.bm.Rule.parse*(*).</action>
<!-- ADD -->
<action type="add" dev="ggregory" due-to="Gary Gregory">Add
HmacUtils.hmac(Path).</action>
<action type="add" dev="ggregory" due-to="Gary Gregory">Add
HmacUtils.hmacHex(Path).</action>
diff --git a/src/main/java/org/apache/commons/codec/language/bm/Lang.java
b/src/main/java/org/apache/commons/codec/language/bm/Lang.java
index d92e37c4..6aacea1a 100644
--- a/src/main/java/org/apache/commons/codec/language/bm/Lang.java
+++ b/src/main/java/org/apache/commons/codec/language/bm/Lang.java
@@ -103,6 +103,8 @@ public class Lang {
private static final String LANGUAGE_RULES_RN =
"/org/apache/commons/codec/language/bm/%s_lang.txt";
+ private static final Pattern PLUS = Pattern.compile("\\+");
+
static {
for (final NameType s : NameType.values()) {
LANGS.put(s, loadFromResource(String.format(LANGUAGE_RULES_RN,
s.getName()), Languages.getInstance(s)));
@@ -163,7 +165,7 @@ public class Lang {
}
// split it up
- final String[] parts = line.split("\\s+");
+ final String[] parts =
ResourceConstants.SPACES.split(line);
if (parts.length != 3) {
throw new IllegalArgumentException("Malformed line '"
+ rawLine +
@@ -171,7 +173,7 @@ public class Lang {
}
final Pattern pattern = Pattern.compile(parts[0]);
- final String[] langs = parts[1].split("\\+");
+ final String[] langs = PLUS.split(parts[1]);
final boolean accept = parts[2].equals("true");
rules.add(new LangRule(pattern, new
HashSet<>(Arrays.asList(langs)), accept));
diff --git
a/src/main/java/org/apache/commons/codec/language/bm/PhoneticEngine.java
b/src/main/java/org/apache/commons/codec/language/bm/PhoneticEngine.java
index 482d6ffd..6b426d7a 100644
--- a/src/main/java/org/apache/commons/codec/language/bm/PhoneticEngine.java
+++ b/src/main/java/org/apache/commons/codec/language/bm/PhoneticEngine.java
@@ -29,6 +29,7 @@ import java.util.Map;
import java.util.Objects;
import java.util.Set;
import java.util.TreeMap;
+import java.util.regex.Pattern;
import java.util.stream.Collectors;
import org.apache.commons.codec.language.bm.Languages.LanguageSet;
@@ -227,6 +228,8 @@ public class PhoneticEngine {
private static final Map<NameType, Set<String>> NAME_PREFIXES = new
EnumMap<>(NameType.class);
+ private static final Pattern QUOTE = Pattern.compile("'");
+
static {
NAME_PREFIXES.put(NameType.ASHKENAZI,
Collections.unmodifiableSet(
@@ -401,14 +404,14 @@ public class PhoneticEngine {
}
}
- final List<String> words = Arrays.asList(input.split("\\s+"));
+ final List<String> words =
Arrays.asList(ResourceConstants.SPACES.split(input));
final List<String> words2 = new ArrayList<>();
// special-case handling of word prefixes based upon the name type
switch (this.nameType) {
case SEPHARDIC:
words.forEach(aWord -> {
- final String[] parts = aWord.split("'", -1);
+ final String[] parts = QUOTE.split(aWord, -1);
words2.add(parts[parts.length - 1]);
});
words2.removeAll(NAME_PREFIXES.get(this.nameType));
diff --git
a/src/main/java/org/apache/commons/codec/language/bm/ResourceConstants.java
b/src/main/java/org/apache/commons/codec/language/bm/ResourceConstants.java
index cee46f59..9b0d4a7a 100644
--- a/src/main/java/org/apache/commons/codec/language/bm/ResourceConstants.java
+++ b/src/main/java/org/apache/commons/codec/language/bm/ResourceConstants.java
@@ -17,6 +17,8 @@
package org.apache.commons.codec.language.bm;
+import java.util.regex.Pattern;
+
import org.apache.commons.codec.CharEncoding;
/**
@@ -32,5 +34,7 @@ final class ResourceConstants {
static final String ENCODING = CharEncoding.UTF_8;
static final String EXT_CMT_END = "*/";
static final String EXT_CMT_START = "/*";
+ static final Pattern SPACES = Pattern.compile("\\s+");
+
}
diff --git a/src/main/java/org/apache/commons/codec/language/bm/Rule.java
b/src/main/java/org/apache/commons/codec/language/bm/Rule.java
index 871af388..5e38c610 100644
--- a/src/main/java/org/apache/commons/codec/language/bm/Rule.java
+++ b/src/main/java/org/apache/commons/codec/language/bm/Rule.java
@@ -300,6 +300,10 @@ public class Rule {
private static final int HASH_INCLUDE_LENGTH = HASH_INCLUDE.length();
+ private static final Pattern AROUND_PLUS = Pattern.compile("[+]");
+
+ private static final Pattern AROUND_PIPE = Pattern.compile("[|]");
+
private static final Map<NameType, Map<RuleType, Map<String, Map<String,
List<Rule>>>>> RULES =
new EnumMap<>(NameType.class);
@@ -452,7 +456,7 @@ public class Rule {
}
final String before = ph.substring(0, open);
final String in = ph.substring(open + 1, ph.length() - 1);
- final Set<String> langs = new
HashSet<>(Arrays.asList(in.split("[+]")));
+ final Set<String> langs = new
HashSet<>(Arrays.asList(AROUND_PLUS.split(in)));
return new Phoneme(before, Languages.LanguageSet.from(langs));
}
@@ -467,7 +471,7 @@ public class Rule {
final List<Phoneme> phs = new ArrayList<>();
final String body = ph.substring(1, ph.length() - 1);
- for (final String part : body.split("[|]")) {
+ for (final String part : AROUND_PIPE.split(body)) {
phs.add(parsePhoneme(part));
}
if (body.startsWith("|") || body.endsWith("|")) {
@@ -521,7 +525,7 @@ public class Rule {
}
} else {
// rule
- final String[] parts = line.split("\\s+");
+ final String[] parts =
ResourceConstants.SPACES.split(line);
if (parts.length != 4) {
throw new IllegalArgumentException("Malformed rule
statement split into " + parts.length +
" parts: " +
rawLine + " in " + location);
