mittens 0.3.0 → 0.3.2

data/vendor/snowball/doc/libstemmer_php_README

@@ -0,0 +1,38 @@
+Snowball stemming library for PHP
+=================================
+
+This is an automatically-generated pure PHP implementation of the Snowball
+stemming algorithms.
+
+The generated code is compatible with PHP 8.3 and later.  The `mbstring`
+extension is required.
+
+It would be possible to extend support to older PHP (back to 7.4) if there's
+demand for it.  Please contact us if this would be useful to you.
+
+This library is intended for situations where the convenience of a pure PHP
+implementation is more important than performance.  If performance
+matters we recommend using the C implementation via bindings instead,
+(for example, using https://github.com/amaccis/php-stemmer).
+
+If you want both the convenience of pure PHP and reasonable performance, we
+suggest avoiding PHP 8.3 as we've noticed the generated stemmers seem to run
+4-5 times faster with PHP >= 8.4 than with 8.3 (this performance gain seems
+much higher than we've seen reported for other PHP code, presumably due to
+something atypical the generated stemmer code does).
+
+How to use library
+------------------
+
+You can stem a word from PHP as follows:
+
+.. code-block:: php
+
+    require 'base-stemmer.php';
+    require 'english-stemmer.php';
+    $stemmer = new SnowballEnglishStemmer;
+    $word = 'compiled';
+    $stem = $stemmer->stemWord($word);
+    printf("%s => %s\n", $word, $stem );
+
+	// prints "compiled => compil"

data/vendor/snowball/doc/libstemmer_python_README

@@ -3,7 +3,7 @@ Snowball stemming library collection for Python
 
 Python 3 (>= 3.3) is supported.  We no longer support Python 2 as the Python
 developers stopped supporting it at the start of 2020.  Snowball 2.1.0 was the
-last release to officially support Python 2; Snowball 3.0.0 was the last
+last release to officially support Python 2; Snowball 3.0.1 was the last
 release which had the code to support Python 2, but we were no longer testing
 it.
 
@@ -45,8 +45,8 @@ The ``snowballstemmer.stemmer`` function takes an algorithm name and returns a
 
    import snowballstemmer
 
-   stemmer = snowballstemmer.stemmer('english');
-   print(stemmer.stemWords("We are the world".split()));
+   stemmer = snowballstemmer.stemmer('english')
+   print(stemmer.stemWords("We are the world".split()))
 
 Generally you should create a stemmer object and reuse it rather than creating
 a fresh object for each word stemmed (since there's some cost to creating and

data/vendor/snowball/examples/stemwords.c

@@ -7,6 +7,11 @@
 #include <string.h> /* for memmove */
 #include <ctype.h>  /* for isupper, tolower */
 
+#ifdef __cplusplus
+// Support compiling as C++ to test code generated by `snowball -c++`.
+# include <exception>
+#endif
+
 #include "libstemmer.h"
 
 const char * progname;
@@ -97,7 +102,9 @@ usage(int n)
           "\n"
           "If -c is given, the argument is the character encoding of the input\n"
           "and output files.  If it is omitted, the UTF-8 encoding is used.\n"
-          "\n"
+          "\n",
+          progname);
+    printf(
           "If -p is given the output file consists of each word of the input\n"
           "file followed by \"->\" followed by its stemmed equivalent.\n"
           "If -p2 is given the output file is a two column layout containing\n"
@@ -106,13 +113,15 @@ usage(int n)
           "Otherwise, the output file consists of the stemmed words, one per\n"
           "line.\n"
           "\n"
-          "-h displays this help\n",
-          progname);
+          "-h displays this help\n");
     exit(n);
 }
 
 int
 main(int argc, char * argv[])
+#ifdef __cplusplus
+try
+#endif
 {
     const char * in = NULL;
     const char * out = NULL;
@@ -202,3 +211,9 @@ main(int argc, char * argv[])
 
     return 0;
 }
+#ifdef __cplusplus
+catch (const std::exception& e) {
+    fprintf(stderr, "Exception: %s\n", e.what());
+    exit(1);
+}
+#endif

data/vendor/snowball/go/README.md

@@ -11,9 +11,12 @@ $ snowball path/to/algorithm.sbl -go -o algorithm
 
 ### Go specific options
 
-`-gop[ackage]` the package name used in the generated go file (defaults to `snowball`)
+`-Package`/`-P`: the package name used in the generated go file (defaults to `snowball`)
 
-`-gor[untime]` the import path used for the Go Snowball runtime (defaults to `github.com/snowballstem/snowball/go`)
+`-goruntime`/`-gor`: the import path used for the Go Snowball runtime (defaults to `github.com/snowballstem/snowball/go`)
+
+Snowball 3.0.1 and earlier supported `-go`/`-gopackage`, but this was just an
+alias for `-Package`/`-P` since Snowball 2.0.0.
 
 ## Code Organization
 
@@ -30,12 +33,17 @@ $ snowball path/to/algorithm.sbl -go -o algorithm
 Assuming you generated a stemmer, put that code in a package which is imported by this code as `english`.
 
 ```
-env := snowball.NewEnv("beautiful")
+env := snowball.NewEnv("")
+env.SetCurrent("beautiful")
 english.Stem(env)
 fmt.Printf("stemmed word is: %s", env.Current())
 ```
 
-NOTE: you can use the env.SetCurrent("new_word") to reuse the env on subsequent calls to the stemmer.
+If you are stemming many words you should reuse `env` as shown above.  If you
+are stemming a single word, you can set the current string when you create it
+with `env:= snowball.NewEnv("beautiful")`, but doing this when stemming many
+words is not recommended as the overhead is measurable (stemwords for the arabic
+stemmer on the sample vocabulary is about 12% faster if you reuse `env`).
 
 ## Testing
 

data/vendor/snowball/go/env.go

@@ -92,10 +92,10 @@ func (env *Env) EqSB(s string) bool {
 	}
 }
 
-func (env *Env) SliceFrom(s string) bool {
+func (env *Env) SliceFrom(s string) {
 	bra, ket := env.Bra, env.Ket
 	env.ReplaceS(bra, ket, s)
-	return true
+	env.Ket = bra + len(s)
 }
 
 func (env *Env) NextChar() {
@@ -112,7 +112,7 @@ func (env *Env) PrevChar() {
 	}
 }
 
-func (env *Env) Hop(delta int32) bool {
+func (env *Env) Hop(delta int) bool {
 	res := env.Cursor
 	for delta > 0 {
 		delta--
@@ -128,11 +128,11 @@ func (env *Env) Hop(delta int32) bool {
 	return true
 }
 
-func (env *Env) HopChecked(delta int32) bool {
+func (env *Env) HopChecked(delta int) bool {
 	return delta >= 0 && env.Hop(delta)
 }
 
-func (env *Env) HopBack(delta int32) bool {
+func (env *Env) HopBack(delta int) bool {
 	res := env.Cursor
 	for delta > 0 {
 		delta--
@@ -148,7 +148,7 @@ func (env *Env) HopBack(delta int32) bool {
 	return true
 }
 
-func (env *Env) HopBackChecked(delta int32) bool {
+func (env *Env) HopBackChecked(delta int) bool {
 	return delta >= 0 && env.HopBack(delta)
 }
 
@@ -310,8 +310,8 @@ func (env *Env) GoOutGroupingB(chars []byte, min, max int32) bool {
 	return false
 }
 
-func (env *Env) SliceDel() bool {
-	return env.SliceFrom("")
+func (env *Env) SliceDel() {
+	env.SliceFrom("")
 }
 
 func (env *Env) Insert(bra, ket int, s string) {
@@ -380,9 +380,8 @@ func (env *Env) FindAmong(amongs []*Among, ctx interface{}) int32 {
 		if commonI >= len(w.Str) {
 			env.Cursor = c + len(w.Str)
 			if w.F != nil {
-				res := w.F(env, ctx)
-				env.Cursor = c + len(w.Str)
-				if res {
+				if w.F(env, ctx) {
+					env.Cursor = c + len(w.Str)
 					return w.B
 				}
 			} else {
@@ -449,9 +448,8 @@ func (env *Env) FindAmongB(amongs []*Among, ctx interface{}) int32 {
 		if commonI >= len(w.Str) {
 			env.Cursor = c - len(w.Str)
 			if w.F != nil {
-				res := w.F(env, ctx)
-				env.Cursor = c - len(w.Str)
-				if res {
+				if w.F(env, ctx) {
+					env.Cursor = c - len(w.Str)
 					return w.B
 				}
 			} else {

data/vendor/snowball/go/stemwords/main.go

@@ -51,9 +51,10 @@ func main() {
 
 	var err error
 	scanner := bufio.NewScanner(reader)
+	env := snowballRuntime.NewEnv("")
 	for scanner.Scan() {
 		word := scanner.Text()
-		env := snowballRuntime.NewEnv(word)
+		env.SetCurrent(word)
 		stemmer(env)
 		fmt.Fprintf(writer, "%s\n", env.Current())
 	}

data/vendor/snowball/java/org/tartarus/snowball/CharArraySequence.java

@@ -0,0 +1,36 @@
+package org.tartarus.snowball;
+
+/**
+ * Internal class used by Snowball stemmers
+ */
+public class CharArraySequence implements CharSequence {
+    public CharArraySequence(char[] a, int len) {
+        this.a = a;
+        this.len = len;
+    }
+
+    final public char charAt(int index) {
+        if (index < 0 || index >= len) {
+            throw new StringIndexOutOfBoundsException(index);
+        }
+        return a[index];
+    }
+
+    final public int length() {
+        return len;
+    }
+
+    final public CharSequence subSequence(int start, int end) {
+        // Not needed for how we used CharSequence.
+        throw new UnsupportedOperationException();
+    }
+
+    final public String toString() {
+        if (a == null) return "";
+        return new String(a, 0, len);
+    }
+
+    final private char[] a;
+
+    final private int len;
+}

data/vendor/snowball/java/org/tartarus/snowball/SnowballProgram.java

@@ -1,13 +1,12 @@
 
 package org.tartarus.snowball;
 import java.lang.reflect.UndeclaredThrowableException;
-import java.io.Serializable;
 import java.util.Arrays;
 
 /**
  * Base class for a snowball stemmer
  */
-public class SnowballProgram implements Serializable {
+public class SnowballProgram {
     protected SnowballProgram()
     {
         cursor = 0;
@@ -17,8 +16,6 @@ public class SnowballProgram implements Serializable {
         ket = limit;
     }
 
-    static final long serialVersionUID = 2016072500L;
-
     /**
      * Set the current string.
      */
@@ -77,7 +74,7 @@ public class SnowballProgram implements Serializable {
     }
 
     // current string
-    private char[] current;
+    protected char[] current;
 
     protected int cursor;
     protected int length;
@@ -290,16 +287,16 @@ public class SnowballProgram implements Serializable {
             if (common_i >= w.s.length) {
                 cursor = c + w.s.length;
                 if (w.method == null) return w.result;
-                boolean res = false;
                 try {
-                    res = (boolean) w.method.invokeExact(this);
+                    if ((boolean) w.method.invokeExact(this)) {
+                        cursor = c + w.s.length;
+                        return w.result;
+                    }
                 } catch (Error | RuntimeException e) {
                     throw e;
                 } catch (Throwable e) {
                     throw new UndeclaredThrowableException(e);
                 }
-                cursor = c + w.s.length;
-                if (res) return w.result;
             }
             i = w.substring_i;
             if (i < 0) return 0;
@@ -354,17 +351,16 @@ public class SnowballProgram implements Serializable {
             if (common_i >= w.s.length) {
                 cursor = c - w.s.length;
                 if (w.method == null) return w.result;
-
-                boolean res = false;
                 try {
-                    res = (boolean) w.method.invokeExact(this);
+                    if ((boolean) w.method.invokeExact(this)) {
+                        cursor = c - w.s.length;
+                        return w.result;
+                    }
                 } catch (Error | RuntimeException e) {
                     throw e;
                 } catch (Throwable e) {
                     throw new UndeclaredThrowableException(e);
                 }
-                cursor = c - w.s.length;
-                if (res) return w.result;
             }
             i = w.substring_i;
             if (i < 0) return 0;
@@ -413,6 +409,7 @@ public class SnowballProgram implements Serializable {
     {
         slice_check();
         replace_s(bra, ket, s);
+        ket = bra + s.length();
     }
 
     protected void slice_del()
@@ -427,35 +424,21 @@ public class SnowballProgram implements Serializable {
         if (c_bra <= ket) ket += adjustment;
     }
 
-    /* Copy the slice into the supplied StringBuilder */
-    protected void slice_to(StringBuilder s)
-    {
-        slice_check();
-        int len = ket - bra;
-        s.setLength(0);
-        s.append(current, bra, len);
-    }
-
-    protected void assign_to(StringBuilder s)
-    {
-        s.setLength(0);
-        s.append(current, 0, limit);
-    }
-
 /*
 extern void debug(struct SN_env * z, int number, int line_count)
-{   int i;
+{
+    int i;
     int limit = SIZE(z->p);
     //if (number >= 0) printf("%3d (line %4d): '", number, line_count);
     if (number >= 0) printf("%3d (line %4d): [%d]'", number, line_count,limit);
-    for (i = 0; i <= limit; i++)
-    {   if (z->lb == i) printf("{");
+    for (i = 0; i <= limit; i++) {
+        if (z->lb == i) printf("{");
         if (z->bra == i) printf("[");
         if (z->c == i) printf("|");
         if (z->ket == i) printf("]");
         if (z->l == i) printf("}");
-        if (i < limit)
-        {   int ch = z->p[i];
+        if (i < limit) {
+            int ch = z->p[i];
             if (ch == 0) ch = '#';
             printf("%c", ch);
         }

data/vendor/snowball/java/org/tartarus/snowball/SnowballStemmer.java

@@ -6,6 +6,4 @@ package org.tartarus.snowball;
  */
 public abstract class SnowballStemmer extends SnowballProgram {
     public abstract boolean stem();
-
-    static final long serialVersionUID = 2016072500L;
 };