Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

noted TooManyClauses catch in QueryParser 

git-svn-id: https://svn.apache.org/repos/asf/lucene/java/trunk@150154 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Erik Hatcher 2003-12-14 17:35:32 +00:00
parent 537368266a
commit 859e6eee20
1 changed files with 111 additions and 111 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

222
src/java/org/apache/lucene/analysis/PorterStemmer.java
View File

@ -61,7 +61,7 @@ package org.apache.lucene.analysis;
Porter, 1980, An algorithm for suffix stripping, Program, Vol. 14, Porter, 1980, An algorithm for suffix stripping, Program, Vol. 14,
no. 3, pp 130-137, no. 3, pp 130-137,
See also http://www.muscat.com/~martin/stem.html See also http://www.tartarus.org/~martin/PorterStemmer/index.html
Bug 1 (reported by Gonzalo Parra 16/10/99) fixed as marked below. Bug 1 (reported by Gonzalo Parra 16/10/99) fixed as marked below.
Tthe words 'aed', 'eed', 'oed' leave k at 'a' for step 3, and b[k-1] Tthe words 'aed', 'eed', 'oed' leave k at 'a' for step 3, and b[k-1]
@ -75,7 +75,7 @@ package org.apache.lucene.analysis;
Release 3. Release 3.
[ This version is derived from Release 3, modified by Brian Goetz to [ This version is derived from Release 3, modified by Brian Goetz to
optimize for fewer object creations. ] optimize for fewer object creations. ]
*/ */
@ -89,11 +89,11 @@ import java.io.*;
* *
* The Stemmer class transforms a word into its root form. The input * The Stemmer class transforms a word into its root form. The input
* word can be provided a character at time (by calling add()), or at once * word can be provided a character at time (by calling add()), or at once
* by calling one of the various stem(something) methods. * by calling one of the various stem(something) methods.
*/ */
class PorterStemmer class PorterStemmer
{ {
private char[] b; private char[] b;
private int i, /* offset into b */ private int i, /* offset into b */
j, k, k0; j, k, k0;
@ -101,12 +101,12 @@ class PorterStemmer
private static final int INC = 50; /* unit of size whereby b is increased */ private static final int INC = 50; /* unit of size whereby b is increased */
private static final int EXTRA = 1; private static final int EXTRA = 1;
public PorterStemmer() { public PorterStemmer() {
b = new char[INC]; b = new char[INC];
i = 0; i = 0;
} }
/** /**
* reset() resets the stemmer so it can stem another word. If you invoke * reset() resets the stemmer so it can stem another word. If you invoke
* the stemmer by calling add(char) and then stem(), you must call reset() * the stemmer by calling add(char) and then stem(), you must call reset()
* before starting another word. * before starting another word.
@ -114,13 +114,13 @@ class PorterStemmer
public void reset() { i = 0; dirty = false; } public void reset() { i = 0; dirty = false; }
/** /**
* Add a character to the word being stemmed. When you are finished * Add a character to the word being stemmed. When you are finished
* adding characters, you can call stem(void) to process the word. * adding characters, you can call stem(void) to process the word.
*/ */
public void add(char ch) { public void add(char ch) {
if (b.length <= i + EXTRA) { if (b.length <= i + EXTRA) {
char[] new_b = new char[b.length+INC]; char[] new_b = new char[b.length+INC];
for (int c = 0; c < b.length; c++) for (int c = 0; c < b.length; c++)
new_b[c] = b[c]; new_b[c] = b[c];
b = new_b; b = new_b;
} }
@ -128,7 +128,7 @@ class PorterStemmer
} }
/** /**
* After a word has been stemmed, it can be retrieved by toString(), * After a word has been stemmed, it can be retrieved by toString(),
* or a reference to the internal buffer can be retrieved by getResultBuffer * or a reference to the internal buffer can be retrieved by getResultBuffer
* and getResultLength (which is generally more efficient.) * and getResultLength (which is generally more efficient.)
*/ */
@ -150,11 +150,11 @@ class PorterStemmer
private final boolean cons(int i) { private final boolean cons(int i) {
switch (b[i]) { switch (b[i]) {
case 'a': case 'e': case 'i': case 'o': case 'u': case 'a': case 'e': case 'i': case 'o': case 'u':
return false; return false;
case 'y': case 'y':
return (i==k0) ? true : !cons(i-1); return (i==k0) ? true : !cons(i-1);
default: default:
return true; return true;
} }
} }
@ -174,27 +174,27 @@ class PorterStemmer
int n = 0; int n = 0;
int i = k0; int i = k0;
while(true) { while(true) {
if (i > j) if (i > j)
return n; return n;
if (! cons(i)) if (! cons(i))
break; break;
i++; i++;
} }
i++; i++;
while(true) { while(true) {
while(true) { while(true) {
if (i > j) if (i > j)
return n; return n;
if (cons(i)) if (cons(i))
break; break;
i++; i++;
} }
i++; i++;
n++; n++;
while(true) { while(true) {
if (i > j) if (i > j)
return n; return n;
if (! cons(i)) if (! cons(i))
break; break;
i++; i++;
} }
@ -205,9 +205,9 @@ class PorterStemmer
/* vowelinstem() is true <=> k0,...j contains a vowel */ /* vowelinstem() is true <=> k0,...j contains a vowel */
private final boolean vowelinstem() { private final boolean vowelinstem() {
int i; int i;
for (i = k0; i <= j; i++) for (i = k0; i <= j; i++)
if (! cons(i)) if (! cons(i))
return true; return true;
return false; return false;
} }
@ -215,9 +215,9 @@ class PorterStemmer
/* doublec(j) is true <=> j,(j-1) contain a double consonant. */ /* doublec(j) is true <=> j,(j-1) contain a double consonant. */
private final boolean doublec(int j) { private final boolean doublec(int j) {
if (j < k0+1) if (j < k0+1)
return false; return false;
if (b[j] != b[j-1]) if (b[j] != b[j-1])
return false; return false;
return cons(j); return cons(j);
} }
@ -232,7 +232,7 @@ class PorterStemmer
*/ */
private final boolean cvc(int i) { private final boolean cvc(int i) {
if (i < k0+2 || !cons(i) || cons(i-1) || !cons(i-2)) if (i < k0+2 || !cons(i) || cons(i-1) || !cons(i-2))
return false; return false;
else { else {
int ch = b[i]; int ch = b[i];
@ -244,10 +244,10 @@ class PorterStemmer
private final boolean ends(String s) { private final boolean ends(String s) {
int l = s.length(); int l = s.length();
int o = k-l+1; int o = k-l+1;
if (o < k0) if (o < k0)
return false; return false;
for (int i = 0; i < l; i++) for (int i = 0; i < l; i++)
if (b[o+i] != s.charAt(i)) if (b[o+i] != s.charAt(i))
return false; return false;
j = k-l; j = k-l;
return true; return true;
@ -259,7 +259,7 @@ class PorterStemmer
void setto(String s) { void setto(String s) {
int l = s.length(); int l = s.length();
int o = j+1; int o = j+1;
for (int i = 0; i < l; i++) for (int i = 0; i < l; i++)
b[o+i] = s.charAt(i); b[o+i] = s.charAt(i);
k = j+l; k = j+l;
dirty = true; dirty = true;
@ -290,37 +290,37 @@ class PorterStemmer
meetings -> meet meetings -> meet
*/ */
private final void step1() { private final void step1() {
if (b[k] == 's') { if (b[k] == 's') {
if (ends("sses")) k -= 2; if (ends("sses")) k -= 2;
else if (ends("ies")) setto("i"); else if (ends("ies")) setto("i");
else if (b[k-1] != 's') k--; else if (b[k-1] != 's') k--;
} }
if (ends("eed")) { if (ends("eed")) {
if (m() > 0) if (m() > 0)
k--; k--;
} }
else if ((ends("ed") || ends("ing")) && vowelinstem()) { else if ((ends("ed") || ends("ing")) && vowelinstem()) {
k = j; k = j;
if (ends("at")) setto("ate"); if (ends("at")) setto("ate");
else if (ends("bl")) setto("ble"); else if (ends("bl")) setto("ble");
else if (ends("iz")) setto("ize"); else if (ends("iz")) setto("ize");
else if (doublec(k)) { else if (doublec(k)) {
int ch = b[k--]; int ch = b[k--];
if (ch == 'l' || ch == 's' || ch == 'z') if (ch == 'l' || ch == 's' || ch == 'z')
k++; k++;
} }
else if (m() == 1 && cvc(k)) else if (m() == 1 && cvc(k))
setto("e"); setto("e");
} }
} }
/* step2() turns terminal y to i when there is another vowel in the stem. */ /* step2() turns terminal y to i when there is another vowel in the stem. */
private final void step2() { private final void step2() {
if (ends("y") && vowelinstem()) { if (ends("y") && vowelinstem()) {
b[k] = 'i'; b[k] = 'i';
dirty = true; dirty = true;
} }
} }
@ -329,122 +329,122 @@ class PorterStemmer
-ation) maps to -ize etc. note that the string before the suffix must give -ation) maps to -ize etc. note that the string before the suffix must give
m() > 0. */ m() > 0. */
private final void step3() { private final void step3() {
if (k == k0) return; /* For Bug 1 */ if (k == k0) return; /* For Bug 1 */
switch (b[k-1]) { switch (b[k-1]) {
case 'a': case 'a':
if (ends("ational")) { r("ate"); break; } if (ends("ational")) { r("ate"); break; }
if (ends("tional")) { r("tion"); break; } if (ends("tional")) { r("tion"); break; }
break; break;
case 'c': case 'c':
if (ends("enci")) { r("ence"); break; } if (ends("enci")) { r("ence"); break; }
if (ends("anci")) { r("ance"); break; } if (ends("anci")) { r("ance"); break; }
break; break;
case 'e': case 'e':
if (ends("izer")) { r("ize"); break; } if (ends("izer")) { r("ize"); break; }
break; break;
case 'l': case 'l':
if (ends("bli")) { r("ble"); break; } if (ends("bli")) { r("ble"); break; }
if (ends("alli")) { r("al"); break; } if (ends("alli")) { r("al"); break; }
if (ends("entli")) { r("ent"); break; } if (ends("entli")) { r("ent"); break; }
if (ends("eli")) { r("e"); break; } if (ends("eli")) { r("e"); break; }
if (ends("ousli")) { r("ous"); break; } if (ends("ousli")) { r("ous"); break; }
break; break;
case 'o': case 'o':
if (ends("ization")) { r("ize"); break; } if (ends("ization")) { r("ize"); break; }
if (ends("ation")) { r("ate"); break; } if (ends("ation")) { r("ate"); break; }
if (ends("ator")) { r("ate"); break; } if (ends("ator")) { r("ate"); break; }
break; break;
case 's': case 's':
if (ends("alism")) { r("al"); break; } if (ends("alism")) { r("al"); break; }
if (ends("iveness")) { r("ive"); break; } if (ends("iveness")) { r("ive"); break; }
if (ends("fulness")) { r("ful"); break; } if (ends("fulness")) { r("ful"); break; }
if (ends("ousness")) { r("ous"); break; } if (ends("ousness")) { r("ous"); break; }
break; break;
case 't': case 't':
if (ends("aliti")) { r("al"); break; } if (ends("aliti")) { r("al"); break; }
if (ends("iviti")) { r("ive"); break; } if (ends("iviti")) { r("ive"); break; }
if (ends("biliti")) { r("ble"); break; } if (ends("biliti")) { r("ble"); break; }
break; break;
case 'g': case 'g':
if (ends("logi")) { r("log"); break; } if (ends("logi")) { r("log"); break; }
} }
} }
/* step4() deals with -ic-, -full, -ness etc. similar strategy to step3. */ /* step4() deals with -ic-, -full, -ness etc. similar strategy to step3. */
private final void step4() { private final void step4() {
switch (b[k]) { switch (b[k]) {
case 'e': case 'e':
if (ends("icate")) { r("ic"); break; } if (ends("icate")) { r("ic"); break; }
if (ends("ative")) { r(""); break; } if (ends("ative")) { r(""); break; }
if (ends("alize")) { r("al"); break; } if (ends("alize")) { r("al"); break; }
break; break;
case 'i': case 'i':
if (ends("iciti")) { r("ic"); break; } if (ends("iciti")) { r("ic"); break; }
break; break;
case 'l': case 'l':
if (ends("ical")) { r("ic"); break; } if (ends("ical")) { r("ic"); break; }
if (ends("ful")) { r(""); break; } if (ends("ful")) { r(""); break; }
break; break;
case 's': case 's':
if (ends("ness")) { r(""); break; } if (ends("ness")) { r(""); break; }
break; break;
} }
} }
/* step5() takes off -ant, -ence etc., in context <c>vcvc<v>. */ /* step5() takes off -ant, -ence etc., in context <c>vcvc<v>. */
private final void step5() { private final void step5() {
if (k == k0) return; /* for Bug 1 */ if (k == k0) return; /* for Bug 1 */
switch (b[k-1]) { switch (b[k-1]) {
case 'a': case 'a':
if (ends("al")) break; if (ends("al")) break;
return; return;
case 'c': case 'c':
if (ends("ance")) break; if (ends("ance")) break;
if (ends("ence")) break; if (ends("ence")) break;
return; return;
case 'e': case 'e':
if (ends("er")) break; return; if (ends("er")) break; return;
case 'i': case 'i':
if (ends("ic")) break; return; if (ends("ic")) break; return;
case 'l': case 'l':
if (ends("able")) break; if (ends("able")) break;
if (ends("ible")) break; return; if (ends("ible")) break; return;
case 'n': case 'n':
if (ends("ant")) break; if (ends("ant")) break;
if (ends("ement")) break; if (ends("ement")) break;
if (ends("ment")) break; if (ends("ment")) break;
/* element etc. not stripped before the m */ /* element etc. not stripped before the m */
if (ends("ent")) break; if (ends("ent")) break;
return; return;
case 'o': case 'o':
if (ends("ion") && j >= 0 && (b[j] == 's' || b[j] == 't')) break; if (ends("ion") && j >= 0 && (b[j] == 's' || b[j] == 't')) break;
/* j >= 0 fixes Bug 2 */ /* j >= 0 fixes Bug 2 */
if (ends("ou")) break; if (ends("ou")) break;
return; return;
/* takes care of -ous */ /* takes care of -ous */
case 's': case 's':
if (ends("ism")) break; if (ends("ism")) break;
return; return;
case 't': case 't':
if (ends("ate")) break; if (ends("ate")) break;
if (ends("iti")) break; if (ends("iti")) break;
return; return;
case 'u': case 'u':
if (ends("ous")) break; if (ends("ous")) break;
return; return;
case 'v': case 'v':
if (ends("ive")) break; if (ends("ive")) break;
return; return;
case 'z': case 'z':
if (ends("ize")) break; if (ends("ize")) break;
return; return;
default: default:
return; return;
} }
if (m() > 1) if (m() > 1)
k = j; k = j;
} }
@ -454,27 +454,27 @@ class PorterStemmer
j = k; j = k;
if (b[k] == 'e') { if (b[k] == 'e') {
int a = m(); int a = m();
if (a > 1 || a == 1 && !cvc(k-1)) if (a > 1 || a == 1 && !cvc(k-1))
k--; k--;
} }
if (b[k] == 'l' && doublec(k) && m() > 1) if (b[k] == 'l' && doublec(k) && m() > 1)
k--; k--;
} }
/** /**
* Stem a word provided as a String. Returns the result as a String. * Stem a word provided as a String. Returns the result as a String.
*/ */
public String stem(String s) { public String stem(String s) {
if (stem(s.toCharArray(), s.length())) if (stem(s.toCharArray(), s.length()))
return toString(); return toString();
else else
return s; return s;
} }
/** Stem a word contained in a char[]. Returns true if the stemming process /** Stem a word contained in a char[]. Returns true if the stemming process
* resulted in a word different from the input. You can retrieve the * resulted in a word different from the input. You can retrieve the
* result with getResultLength()/getResultBuffer() or toString(). * result with getResultLength()/getResultBuffer() or toString().
*/ */
public boolean stem(char[] word) { public boolean stem(char[] word) {
return stem(word, word.length); return stem(word, word.length);
@ -483,7 +483,7 @@ class PorterStemmer
/** Stem a word contained in a portion of a char[] array. Returns /** Stem a word contained in a portion of a char[] array. Returns
* true if the stemming process resulted in a word different from * true if the stemming process resulted in a word different from
* the input. You can retrieve the result with * the input. You can retrieve the result with
* getResultLength()/getResultBuffer() or toString(). * getResultLength()/getResultBuffer() or toString().
*/ */
public boolean stem(char[] wordBuffer, int offset, int wordLen) { public boolean stem(char[] wordBuffer, int offset, int wordLen) {
reset(); reset();
@ -491,7 +491,7 @@ class PorterStemmer
char[] new_b = new char[wordLen + EXTRA]; char[] new_b = new char[wordLen + EXTRA];
b = new_b; b = new_b;
} }
for (int j=0; j<wordLen; j++) for (int j=0; j<wordLen; j++)
b[j] = wordBuffer[offset+j]; b[j] = wordBuffer[offset+j];
i = wordLen; i = wordLen;
return stem(0); return stem(0);
@ -500,7 +500,7 @@ class PorterStemmer
/** Stem a word contained in a leading portion of a char[] array. /** Stem a word contained in a leading portion of a char[] array.
* Returns true if the stemming process resulted in a word different * Returns true if the stemming process resulted in a word different
* from the input. You can retrieve the result with * from the input. You can retrieve the result with
* getResultLength()/getResultBuffer() or toString(). * getResultLength()/getResultBuffer() or toString().
*/ */
public boolean stem(char[] word, int wordLen) { public boolean stem(char[] word, int wordLen) {
return stem(word, 0, wordLen); return stem(word, 0, wordLen);
@ -509,17 +509,17 @@ class PorterStemmer
/** Stem the word placed into the Stemmer buffer through calls to add(). /** Stem the word placed into the Stemmer buffer through calls to add().
* Returns true if the stemming process resulted in a word different * Returns true if the stemming process resulted in a word different
* from the input. You can retrieve the result with * from the input. You can retrieve the result with
* getResultLength()/getResultBuffer() or toString(). * getResultLength()/getResultBuffer() or toString().
*/ */
public boolean stem() { public boolean stem() {
return stem(0); return stem(0);
} }
public boolean stem(int i0) { public boolean stem(int i0) {
k = i - 1; k = i - 1;
k0 = i0; k0 = i0;
if (k > k0+1) { if (k > k0+1) {
step1(); step2(); step3(); step4(); step5(); step6(); step1(); step2(); step3(); step4(); step5(); step6();
} }
// Also, a word is considered dirty if we lopped off letters // Also, a word is considered dirty if we lopped off letters
// Thanks to Ifigenia Vairelles for pointing this out. // Thanks to Ifigenia Vairelles for pointing this out.
@ -530,8 +530,8 @@ class PorterStemmer
} }
/** Test program for demonstrating the Stemmer. It reads a file and /** Test program for demonstrating the Stemmer. It reads a file and
* stems each word, writing the result to standard out. * stems each word, writing the result to standard out.
* Usage: Stemmer file-name * Usage: Stemmer file-name
*/ */
public static void main(String[] args) { public static void main(String[] args) {
PorterStemmer s = new PorterStemmer(); PorterStemmer s = new PorterStemmer();
@ -546,26 +546,26 @@ class PorterStemmer
offset = 0; offset = 0;
s.reset(); s.reset();
while(true) { while(true) {
if (offset < bufferLen) if (offset < bufferLen)
ch = buffer[offset++]; ch = buffer[offset++];
else { else {
bufferLen = in.read(buffer); bufferLen = in.read(buffer);
offset = 0; offset = 0;
if (bufferLen < 0) if (bufferLen < 0)
ch = -1; ch = -1;
else else
ch = buffer[offset++]; ch = buffer[offset++];
} }
if (Character.isLetter((char) ch)) { if (Character.isLetter((char) ch)) {
s.add(Character.toLowerCase((char) ch)); s.add(Character.toLowerCase((char) ch));
} }
else { else {
s.stem(); s.stem();
System.out.print(s.toString()); System.out.print(s.toString());
s.reset(); s.reset();
if (ch < 0) if (ch < 0)
break; break;
else { else {
System.out.print((char) ch); System.out.print((char) ch);
@ -575,7 +575,7 @@ class PorterStemmer
in.close(); in.close();
} }
catch (IOException e) { catch (IOException e) {
System.out.println("error reading " + args[i]); System.out.println("error reading " + args[i]);
} }
} }