ruby-stemmer 0.9.3-x86-mingw32

data/libstemmer_c/libstemmer/modules_utf8.txt

@@ -0,0 +1,50 @@
+# This file contains a list of stemmers to include in the distribution.
+# The format is a set of space separated lines - on each line:
+#  First item is name of stemmer.
+#  Second item is comma separated list of character sets.
+#  Third item is comma separated list of names to refer to the stemmer by.
+#
+# Lines starting with a #, or blank lines, are ignored.
+
+# List all the main algorithms for each language, in UTF-8.
+
+latin           UTF_8                   latin
+danish          UTF_8                   danish,da,dan
+dutch           UTF_8                   dutch,nl,dut,nld
+english         UTF_8                   english,en,eng
+finnish         UTF_8                   finnish,fi,fin
+french          UTF_8                   french,fr,fre,fra
+german          UTF_8                   german,de,ger,deu
+hungarian       UTF_8                   hungarian,hu,hun
+italian         UTF_8                   italian,it,ita
+norwegian       UTF_8                   norwegian,no,nor
+portuguese      UTF_8                   portuguese,pt,por
+romanian        UTF_8                   romanian,ro,rum,ron
+russian         UTF_8                   russian,ru,rus
+spanish         UTF_8                   spanish,es,esl,spa
+swedish         UTF_8                   swedish,sv,swe
+turkish         UTF_8                   turkish,tr,tur
+
+# Also include the traditional porter algorithm for english.
+# The porter algorithm is included in the libstemmer distribution to assist
+# with backwards compatibility, but for new systems the english algorithm
+# should be used in preference.
+porter          UTF_8                   porter
+
+# Some other stemmers in the snowball project are not included in the standard
+# distribution. To compile a libstemmer with them in, add them to this list,
+# and regenerate the distribution. (You will need a full source checkout for
+# this.) They are included in the snowball website as curiosities, but are not
+# intended for general use, and use of them is is not fully supported.  These
+# algorithms are:
+#
+# german2          - This is a slight modification of the german stemmer.
+#german2          UTF_8                   german2
+#
+# kraaij_pohlmann  - This is a different dutch stemmer.
+#kraaij_pohlmann  UTF_8                   kraaij_pohlmann
+#
+# lovins           - This is an english stemmer, but fairly outdated, and
+#                    only really applicable to a restricted type of input text
+#                    (keywords in academic publications).
+#lovins           UTF_8                   lovins

data/libstemmer_c/mkinc.mak

@@ -0,0 +1,86 @@
+# libstemmer/mkinc.mak: List of stemming module source files
+#
+# This file is generated by mkmodules.pl from a list of module names.
+# Do not edit manually.
+#
+# Modules included by this file are: latin, danish, dutch, english, finnish, french,
+# german, hungarian, italian, norwegian, porter, portuguese, romanian,
+# russian, spanish, swedish, turkish
+
+snowball_sources= \
+  src_c/stem_ISO_8859_1_latin.c \
+  src_c/stem_UTF_8_latin.c \
+  src_c/stem_ISO_8859_1_danish.c \
+  src_c/stem_UTF_8_danish.c \
+  src_c/stem_ISO_8859_1_dutch.c \
+  src_c/stem_UTF_8_dutch.c \
+  src_c/stem_ISO_8859_1_english.c \
+  src_c/stem_UTF_8_english.c \
+  src_c/stem_ISO_8859_1_finnish.c \
+  src_c/stem_UTF_8_finnish.c \
+  src_c/stem_ISO_8859_1_french.c \
+  src_c/stem_UTF_8_french.c \
+  src_c/stem_ISO_8859_1_german.c \
+  src_c/stem_UTF_8_german.c \
+  src_c/stem_ISO_8859_1_hungarian.c \
+  src_c/stem_UTF_8_hungarian.c \
+  src_c/stem_ISO_8859_1_italian.c \
+  src_c/stem_UTF_8_italian.c \
+  src_c/stem_ISO_8859_1_norwegian.c \
+  src_c/stem_UTF_8_norwegian.c \
+  src_c/stem_ISO_8859_1_porter.c \
+  src_c/stem_UTF_8_porter.c \
+  src_c/stem_ISO_8859_1_portuguese.c \
+  src_c/stem_UTF_8_portuguese.c \
+  src_c/stem_ISO_8859_2_romanian.c \
+  src_c/stem_UTF_8_romanian.c \
+  src_c/stem_KOI8_R_russian.c \
+  src_c/stem_UTF_8_russian.c \
+  src_c/stem_ISO_8859_1_spanish.c \
+  src_c/stem_UTF_8_spanish.c \
+  src_c/stem_ISO_8859_1_swedish.c \
+  src_c/stem_UTF_8_swedish.c \
+  src_c/stem_UTF_8_turkish.c \
+  runtime/api.c \
+  runtime/utilities.c \
+  libstemmer/libstemmer.c
+
+snowball_headers= \
+  src_c/stem_ISO_8859_1_latin.h \
+  src_c/stem_UTF_8_latin.h \
+  src_c/stem_ISO_8859_1_danish.h \
+  src_c/stem_UTF_8_danish.h \
+  src_c/stem_ISO_8859_1_dutch.h \
+  src_c/stem_UTF_8_dutch.h \
+  src_c/stem_ISO_8859_1_english.h \
+  src_c/stem_UTF_8_english.h \
+  src_c/stem_ISO_8859_1_finnish.h \
+  src_c/stem_UTF_8_finnish.h \
+  src_c/stem_ISO_8859_1_french.h \
+  src_c/stem_UTF_8_french.h \
+  src_c/stem_ISO_8859_1_german.h \
+  src_c/stem_UTF_8_german.h \
+  src_c/stem_ISO_8859_1_hungarian.h \
+  src_c/stem_UTF_8_hungarian.h \
+  src_c/stem_ISO_8859_1_italian.h \
+  src_c/stem_UTF_8_italian.h \
+  src_c/stem_ISO_8859_1_norwegian.h \
+  src_c/stem_UTF_8_norwegian.h \
+  src_c/stem_ISO_8859_1_porter.h \
+  src_c/stem_UTF_8_porter.h \
+  src_c/stem_ISO_8859_1_portuguese.h \
+  src_c/stem_UTF_8_portuguese.h \
+  src_c/stem_ISO_8859_2_romanian.h \
+  src_c/stem_UTF_8_romanian.h \
+  src_c/stem_KOI8_R_russian.h \
+  src_c/stem_UTF_8_russian.h \
+  src_c/stem_ISO_8859_1_spanish.h \
+  src_c/stem_UTF_8_spanish.h \
+  src_c/stem_ISO_8859_1_swedish.h \
+  src_c/stem_UTF_8_swedish.h \
+  src_c/stem_UTF_8_turkish.h \
+  include/libstemmer.h \
+  libstemmer/modules.h \
+  runtime/api.h \
+  runtime/header.h
+

data/libstemmer_c/mkinc_utf8.mak

@@ -0,0 +1,54 @@
+# libstemmer/mkinc_utf8.mak: List of stemming module source files
+#
+# This file is generated by mkmodules.pl from a list of module names.
+# Do not edit manually.
+#
+# Modules included by this file are: danish, dutch, english, finnish, french,
+# german, hungarian, italian, norwegian, porter, portuguese, romanian,
+# russian, spanish, swedish, turkish
+
+snowball_sources= \
+  src_c/stem_UTF_8_latin.c \
+  src_c/stem_UTF_8_danish.c \
+  src_c/stem_UTF_8_dutch.c \
+  src_c/stem_UTF_8_english.c \
+  src_c/stem_UTF_8_finnish.c \
+  src_c/stem_UTF_8_french.c \
+  src_c/stem_UTF_8_german.c \
+  src_c/stem_UTF_8_hungarian.c \
+  src_c/stem_UTF_8_italian.c \
+  src_c/stem_UTF_8_norwegian.c \
+  src_c/stem_UTF_8_porter.c \
+  src_c/stem_UTF_8_portuguese.c \
+  src_c/stem_UTF_8_romanian.c \
+  src_c/stem_UTF_8_russian.c \
+  src_c/stem_UTF_8_spanish.c \
+  src_c/stem_UTF_8_swedish.c \
+  src_c/stem_UTF_8_turkish.c \
+  runtime/api.c \
+  runtime/utilities.c \
+  libstemmer/libstemmer_utf8.c
+
+snowball_headers= \
+  src_c/stem_UTF_8_latin.h \
+  src_c/stem_UTF_8_danish.h \
+  src_c/stem_UTF_8_dutch.h \
+  src_c/stem_UTF_8_english.h \
+  src_c/stem_UTF_8_finnish.h \
+  src_c/stem_UTF_8_french.h \
+  src_c/stem_UTF_8_german.h \
+  src_c/stem_UTF_8_hungarian.h \
+  src_c/stem_UTF_8_italian.h \
+  src_c/stem_UTF_8_norwegian.h \
+  src_c/stem_UTF_8_porter.h \
+  src_c/stem_UTF_8_portuguese.h \
+  src_c/stem_UTF_8_romanian.h \
+  src_c/stem_UTF_8_russian.h \
+  src_c/stem_UTF_8_spanish.h \
+  src_c/stem_UTF_8_swedish.h \
+  src_c/stem_UTF_8_turkish.h \
+  include/libstemmer.h \
+  libstemmer/modules_utf8.h \
+  runtime/api.h \
+  runtime/header.h
+

data/libstemmer_c/runtime/api.c

@@ -0,0 +1,66 @@
+
+#include <stdlib.h> /* for calloc, free */
+#include "header.h"
+
+extern struct SN_env * SN_create_env(int S_size, int I_size, int B_size)
+{
+    struct SN_env * z = (struct SN_env *) calloc(1, sizeof(struct SN_env));
+    if (z == NULL) return NULL;
+    z->p = create_s();
+    if (z->p == NULL) goto error;
+    if (S_size)
+    {
+        int i;
+        z->S = (symbol * *) calloc(S_size, sizeof(symbol *));
+        if (z->S == NULL) goto error;
+
+        for (i = 0; i < S_size; i++)
+        {
+            z->S[i] = create_s();
+            if (z->S[i] == NULL) goto error;
+        }
+    }
+
+    if (I_size)
+    {
+        z->I = (int *) calloc(I_size, sizeof(int));
+        if (z->I == NULL) goto error;
+    }
+
+    if (B_size)
+    {
+        z->B = (unsigned char *) calloc(B_size, sizeof(unsigned char));
+        if (z->B == NULL) goto error;
+    }
+
+    return z;
+error:
+    SN_close_env(z, S_size);
+    return NULL;
+}
+
+extern void SN_close_env(struct SN_env * z, int S_size)
+{
+    if (z == NULL) return;
+    if (S_size)
+    {
+        int i;
+        for (i = 0; i < S_size; i++)
+        {
+            lose_s(z->S[i]);
+        }
+        free(z->S);
+    }
+    free(z->I);
+    free(z->B);
+    if (z->p) lose_s(z->p);
+    free(z);
+}
+
+extern int SN_set_current(struct SN_env * z, int size, const symbol * s)
+{
+    int err = replace_s(z, 0, z->l, size, s, NULL);
+    z->c = 0;
+    return err;
+}
+

data/libstemmer_c/runtime/api.h

@@ -0,0 +1,26 @@
+
+typedef unsigned char symbol;
+
+/* Or replace 'char' above with 'short' for 16 bit characters.
+
+   More precisely, replace 'char' with whatever type guarantees the
+   character width you need. Note however that sizeof(symbol) should divide
+   HEAD, defined in header.h as 2*sizeof(int), without remainder, otherwise
+   there is an alignment problem. In the unlikely event of a problem here,
+   consult Martin Porter.
+
+*/
+
+struct SN_env {
+    symbol * p;
+    int c; int l; int lb; int bra; int ket;
+    symbol * * S;
+    int * I;
+    unsigned char * B;
+};
+
+extern struct SN_env * SN_create_env(int S_size, int I_size, int B_size);
+extern void SN_close_env(struct SN_env * z, int S_size);
+
+extern int SN_set_current(struct SN_env * z, int size, const symbol * s);
+

data/libstemmer_c/runtime/header.h

@@ -0,0 +1,58 @@
+
+#include <limits.h>
+
+#include "api.h"
+
+#define MAXINT INT_MAX
+#define MININT INT_MIN
+
+#define HEAD 2*sizeof(int)
+
+#define SIZE(p)        ((int *)(p))[-1]
+#define SET_SIZE(p, n) ((int *)(p))[-1] = n
+#define CAPACITY(p)    ((int *)(p))[-2]
+
+struct among
+{   int s_size;     /* number of chars in string */
+    const symbol * s;       /* search string */
+    int substring_i;/* index to longest matching substring */
+    int result;     /* result of the lookup */
+    int (* function)(struct SN_env *);
+};
+
+extern symbol * create_s(void);
+extern void lose_s(symbol * p);
+
+extern int skip_utf8(const symbol * p, int c, int lb, int l, int n);
+
+extern int in_grouping_U(struct SN_env * z, const unsigned char * s, int min, int max, int repeat);
+extern int in_grouping_b_U(struct SN_env * z, const unsigned char * s, int min, int max, int repeat);
+extern int out_grouping_U(struct SN_env * z, const unsigned char * s, int min, int max, int repeat);
+extern int out_grouping_b_U(struct SN_env * z, const unsigned char * s, int min, int max, int repeat);
+
+extern int in_grouping(struct SN_env * z, const unsigned char * s, int min, int max, int repeat);
+extern int in_grouping_b(struct SN_env * z, const unsigned char * s, int min, int max, int repeat);
+extern int out_grouping(struct SN_env * z, const unsigned char * s, int min, int max, int repeat);
+extern int out_grouping_b(struct SN_env * z, const unsigned char * s, int min, int max, int repeat);
+
+extern int eq_s(struct SN_env * z, int s_size, const symbol * s);
+extern int eq_s_b(struct SN_env * z, int s_size, const symbol * s);
+extern int eq_v(struct SN_env * z, const symbol * p);
+extern int eq_v_b(struct SN_env * z, const symbol * p);
+
+extern int find_among(struct SN_env * z, const struct among * v, int v_size);
+extern int find_among_b(struct SN_env * z, const struct among * v, int v_size);
+
+extern int replace_s(struct SN_env * z, int c_bra, int c_ket, int s_size, const symbol * s, int * adjustment);
+extern int slice_from_s(struct SN_env * z, int s_size, const symbol * s);
+extern int slice_from_v(struct SN_env * z, const symbol * p);
+extern int slice_del(struct SN_env * z);
+
+extern int insert_s(struct SN_env * z, int bra, int ket, int s_size, const symbol * s);
+extern int insert_v(struct SN_env * z, int bra, int ket, const symbol * p);
+
+extern symbol * slice_to(struct SN_env * z, symbol * p);
+extern symbol * assign_to(struct SN_env * z, symbol * p);
+
+extern void debug(struct SN_env * z, int number, int line_count);
+

data/libstemmer_c/runtime/utilities.c

@@ -0,0 +1,478 @@
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "header.h"
+
+#define unless(C) if(!(C))
+
+#define CREATE_SIZE 1
+
+extern symbol * create_s(void) {
+    symbol * p;
+    void * mem = malloc(HEAD + (CREATE_SIZE + 1) * sizeof(symbol));
+    if (mem == NULL) return NULL;
+    p = (symbol *) (HEAD + (char *) mem);
+    CAPACITY(p) = CREATE_SIZE;
+    SET_SIZE(p, CREATE_SIZE);
+    return p;
+}
+
+extern void lose_s(symbol * p) {
+    if (p == NULL) return;
+    free((char *) p - HEAD);
+}
+
+/*
+   new_p = skip_utf8(p, c, lb, l, n); skips n characters forwards from p + c
+   if n +ve, or n characters backwards from p + c - 1 if n -ve. new_p is the new
+   position, or 0 on failure.
+
+   -- used to implement hop and next in the utf8 case.
+*/
+
+extern int skip_utf8(const symbol * p, int c, int lb, int l, int n) {
+    int b;
+    if (n >= 0) {
+        for (; n > 0; n--) {
+            if (c >= l) return -1;
+            b = p[c++];
+            if (b >= 0xC0) {   /* 1100 0000 */
+                while (c < l) {
+                    b = p[c];
+                    if (b >= 0xC0 || b < 0x80) break;
+                    /* break unless b is 10------ */
+                    c++;
+                }
+            }
+        }
+    } else {
+        for (; n < 0; n++) {
+            if (c <= lb) return -1;
+            b = p[--c];
+            if (b >= 0x80) {   /* 1000 0000 */
+                while (c > lb) {
+                    b = p[c];
+                    if (b >= 0xC0) break; /* 1100 0000 */
+                    c--;
+                }
+            }
+        }
+    }
+    return c;
+}
+
+/* Code for character groupings: utf8 cases */
+
+static int get_utf8(const symbol * p, int c, int l, int * slot) {
+    int b0, b1;
+    if (c >= l) return 0;
+    b0 = p[c++];
+    if (b0 < 0xC0 || c == l) {   /* 1100 0000 */
+        * slot = b0; return 1;
+    }
+    b1 = p[c++];
+    if (b0 < 0xE0 || c == l) {   /* 1110 0000 */
+        * slot = (b0 & 0x1F) << 6 | (b1 & 0x3F); return 2;
+    }
+    * slot = (b0 & 0xF) << 12 | (b1 & 0x3F) << 6 | (p[c] & 0x3F); return 3;
+}
+
+static int get_b_utf8(const symbol * p, int c, int lb, int * slot) {
+    int b0, b1;
+    if (c <= lb) return 0;
+    b0 = p[--c];
+    if (b0 < 0x80 || c == lb) {   /* 1000 0000 */
+        * slot = b0; return 1;
+    }
+    b1 = p[--c];
+    if (b1 >= 0xC0 || c == lb) {   /* 1100 0000 */
+        * slot = (b1 & 0x1F) << 6 | (b0 & 0x3F); return 2;
+    }
+    * slot = (p[c] & 0xF) << 12 | (b1 & 0x3F) << 6 | (b0 & 0x3F); return 3;
+}
+
+extern int in_grouping_U(struct SN_env * z, const unsigned char * s, int min, int max, int repeat) {
+    do {
+	int ch;
+	int w = get_utf8(z->p, z->c, z->l, & ch);
+	unless (w) return -1;
+	if (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0)
+	    return w;
+	z->c += w;
+    } while (repeat);
+    return 0;
+}
+
+extern int in_grouping_b_U(struct SN_env * z, const unsigned char * s, int min, int max, int repeat) {
+    do {
+	int ch;
+	int w = get_b_utf8(z->p, z->c, z->lb, & ch);
+	unless (w) return -1;
+	if (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0)
+	    return w;
+	z->c -= w;
+    } while (repeat);
+    return 0;
+}
+
+extern int out_grouping_U(struct SN_env * z, const unsigned char * s, int min, int max, int repeat) {
+    do {
+	int ch;
+	int w = get_utf8(z->p, z->c, z->l, & ch);
+	unless (w) return -1;
+	unless (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0)
+	    return w;
+	z->c += w;
+    } while (repeat);
+    return 0;
+}
+
+extern int out_grouping_b_U(struct SN_env * z, const unsigned char * s, int min, int max, int repeat) {
+    do {
+	int ch;
+	int w = get_b_utf8(z->p, z->c, z->lb, & ch);
+	unless (w) return -1;
+	unless (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0)
+	    return w;
+	z->c -= w;
+    } while (repeat);
+    return 0;
+}
+
+/* Code for character groupings: non-utf8 cases */
+
+extern int in_grouping(struct SN_env * z, const unsigned char * s, int min, int max, int repeat) {
+    do {
+	int ch;
+	if (z->c >= z->l) return -1;
+	ch = z->p[z->c];
+	if (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0)
+	    return 1;
+	z->c++;
+    } while (repeat);
+    return 0;
+}
+
+extern int in_grouping_b(struct SN_env * z, const unsigned char * s, int min, int max, int repeat) {
+    do {
+	int ch;
+	if (z->c <= z->lb) return -1;
+	ch = z->p[z->c - 1];
+	if (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0)
+	    return 1;
+	z->c--;
+    } while (repeat);
+    return 0;
+}
+
+extern int out_grouping(struct SN_env * z, const unsigned char * s, int min, int max, int repeat) {
+    do {
+	int ch;
+	if (z->c >= z->l) return -1;
+	ch = z->p[z->c];
+	unless (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0)
+	    return 1;
+	z->c++;
+    } while (repeat);
+    return 0;
+}
+
+extern int out_grouping_b(struct SN_env * z, const unsigned char * s, int min, int max, int repeat) {
+    do {
+	int ch;
+	if (z->c <= z->lb) return -1;
+	ch = z->p[z->c - 1];
+	unless (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0)
+	    return 1;
+	z->c--;
+    } while (repeat);
+    return 0;
+}
+
+extern int eq_s(struct SN_env * z, int s_size, const symbol * s) {
+    if (z->l - z->c < s_size || memcmp(z->p + z->c, s, s_size * sizeof(symbol)) != 0) return 0;
+    z->c += s_size; return 1;
+}
+
+extern int eq_s_b(struct SN_env * z, int s_size, const symbol * s) {
+    if (z->c - z->lb < s_size || memcmp(z->p + z->c - s_size, s, s_size * sizeof(symbol)) != 0) return 0;
+    z->c -= s_size; return 1;
+}
+
+extern int eq_v(struct SN_env * z, const symbol * p) {
+    return eq_s(z, SIZE(p), p);
+}
+
+extern int eq_v_b(struct SN_env * z, const symbol * p) {
+    return eq_s_b(z, SIZE(p), p);
+}
+
+extern int find_among(struct SN_env * z, const struct among * v, int v_size) {
+
+    int i = 0;
+    int j = v_size;
+
+    int c = z->c; int l = z->l;
+    symbol * q = z->p + c;
+
+    const struct among * w;
+
+    int common_i = 0;
+    int common_j = 0;
+
+    int first_key_inspected = 0;
+
+    while(1) {
+        int k = i + ((j - i) >> 1);
+        int diff = 0;
+        int common = common_i < common_j ? common_i : common_j; /* smaller */
+        w = v + k;
+        {
+            int i2; for (i2 = common; i2 < w->s_size; i2++) {
+                if (c + common == l) { diff = -1; break; }
+                diff = q[common] - w->s[i2];
+                if (diff != 0) break;
+                common++;
+            }
+        }
+        if (diff < 0) { j = k; common_j = common; }
+                 else { i = k; common_i = common; }
+        if (j - i <= 1) {
+            if (i > 0) break; /* v->s has been inspected */
+            if (j == i) break; /* only one item in v */
+
+            /* - but now we need to go round once more to get
+               v->s inspected. This looks messy, but is actually
+               the optimal approach.  */
+
+            if (first_key_inspected) break;
+            first_key_inspected = 1;
+        }
+    }
+    while(1) {
+        w = v + i;
+        if (common_i >= w->s_size) {
+            z->c = c + w->s_size;
+            if (w->function == 0) return w->result;
+            {
+                int res = w->function(z);
+                z->c = c + w->s_size;
+                if (res) return w->result;
+            }
+        }
+        i = w->substring_i;
+        if (i < 0) return 0;
+    }
+}
+
+/* find_among_b is for backwards processing. Same comments apply */
+
+extern int find_among_b(struct SN_env * z, const struct among * v, int v_size) {
+
+    int i = 0;
+    int j = v_size;
+
+    int c = z->c; int lb = z->lb;
+    symbol * q = z->p + c - 1;
+
+    const struct among * w;
+
+    int common_i = 0;
+    int common_j = 0;
+
+    int first_key_inspected = 0;
+
+    while(1) {
+        int k = i + ((j - i) >> 1);
+        int diff = 0;
+        int common = common_i < common_j ? common_i : common_j;
+        w = v + k;
+        {
+            int i2; for (i2 = w->s_size - 1 - common; i2 >= 0; i2--) {
+                if (c - common == lb) { diff = -1; break; }
+                diff = q[- common] - w->s[i2];
+                if (diff != 0) break;
+                common++;
+            }
+        }
+        if (diff < 0) { j = k; common_j = common; }
+                 else { i = k; common_i = common; }
+        if (j - i <= 1) {
+            if (i > 0) break;
+            if (j == i) break;
+            if (first_key_inspected) break;
+            first_key_inspected = 1;
+        }
+    }
+    while(1) {
+        w = v + i;
+        if (common_i >= w->s_size) {
+            z->c = c - w->s_size;
+            if (w->function == 0) return w->result;
+            {
+                int res = w->function(z);
+                z->c = c - w->s_size;
+                if (res) return w->result;
+            }
+        }
+        i = w->substring_i;
+        if (i < 0) return 0;
+    }
+}
+
+
+/* Increase the size of the buffer pointed to by p to at least n symbols.
+ * If insufficient memory, returns NULL and frees the old buffer.
+ */
+static symbol * increase_size(symbol * p, int n) {
+    symbol * q;
+    int new_size = n + 20;
+    void * mem = realloc((char *) p - HEAD,
+                         HEAD + (new_size + 1) * sizeof(symbol));
+    if (mem == NULL) {
+        lose_s(p);
+        return NULL;
+    }
+    q = (symbol *) (HEAD + (char *)mem);
+    CAPACITY(q) = new_size;
+    return q;
+}
+
+/* to replace symbols between c_bra and c_ket in z->p by the
+   s_size symbols at s.
+   Returns 0 on success, -1 on error.
+   Also, frees z->p (and sets it to NULL) on error.
+*/
+extern int replace_s(struct SN_env * z, int c_bra, int c_ket, int s_size, const symbol * s, int * adjptr)
+{
+    int adjustment;
+    int len;
+    if (z->p == NULL) {
+        z->p = create_s();
+        if (z->p == NULL) return -1;
+    }
+    adjustment = s_size - (c_ket - c_bra);
+    len = SIZE(z->p);
+    if (adjustment != 0) {
+        if (adjustment + len > CAPACITY(z->p)) {
+            z->p = increase_size(z->p, adjustment + len);
+            if (z->p == NULL) return -1;
+        }
+        memmove(z->p + c_ket + adjustment,
+                z->p + c_ket,
+                (len - c_ket) * sizeof(symbol));
+        SET_SIZE(z->p, adjustment + len);
+        z->l += adjustment;
+        if (z->c >= c_ket)
+            z->c += adjustment;
+        else
+            if (z->c > c_bra)
+                z->c = c_bra;
+    }
+    unless (s_size == 0) memmove(z->p + c_bra, s, s_size * sizeof(symbol));
+    if (adjptr != NULL)
+        *adjptr = adjustment;
+    return 0;
+}
+
+static int slice_check(struct SN_env * z) {
+
+    if (z->bra < 0 ||
+        z->bra > z->ket ||
+        z->ket > z->l ||
+        z->p == NULL ||
+        z->l > SIZE(z->p)) /* this line could be removed */
+    {
+#if 0
+        fprintf(stderr, "faulty slice operation:\n");
+        debug(z, -1, 0);
+#endif
+        return -1;
+    }
+    return 0;
+}
+
+extern int slice_from_s(struct SN_env * z, int s_size, const symbol * s) {
+    if (slice_check(z)) return -1;
+    return replace_s(z, z->bra, z->ket, s_size, s, NULL);
+}
+
+extern int slice_from_v(struct SN_env * z, const symbol * p) {
+    return slice_from_s(z, SIZE(p), p);
+}
+
+extern int slice_del(struct SN_env * z) {
+    return slice_from_s(z, 0, 0);
+}
+
+extern int insert_s(struct SN_env * z, int bra, int ket, int s_size, const symbol * s) {
+    int adjustment;
+    if (replace_s(z, bra, ket, s_size, s, &adjustment))
+        return -1;
+    if (bra <= z->bra) z->bra += adjustment;
+    if (bra <= z->ket) z->ket += adjustment;
+    return 0;
+}
+
+extern int insert_v(struct SN_env * z, int bra, int ket, const symbol * p) {
+    int adjustment;
+    if (replace_s(z, bra, ket, SIZE(p), p, &adjustment))
+        return -1;
+    if (bra <= z->bra) z->bra += adjustment;
+    if (bra <= z->ket) z->ket += adjustment;
+    return 0;
+}
+
+extern symbol * slice_to(struct SN_env * z, symbol * p) {
+    if (slice_check(z)) {
+        lose_s(p);
+        return NULL;
+    }
+    {
+        int len = z->ket - z->bra;
+        if (CAPACITY(p) < len) {
+            p = increase_size(p, len);
+            if (p == NULL)
+                return NULL;
+        }
+        memmove(p, z->p + z->bra, len * sizeof(symbol));
+        SET_SIZE(p, len);
+    }
+    return p;
+}
+
+extern symbol * assign_to(struct SN_env * z, symbol * p) {
+    int len = z->l;
+    if (CAPACITY(p) < len) {
+        p = increase_size(p, len);
+        if (p == NULL)
+            return NULL;
+    }
+    memmove(p, z->p, len * sizeof(symbol));
+    SET_SIZE(p, len);
+    return p;
+}
+
+#if 0
+extern void debug(struct SN_env * z, int number, int line_count) {
+    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("{");
+        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 (ch == 0) ch = '#';
+            printf("%c", ch);
+        }
+    }
+    printf("'\n");
+}
+#endif