recent changes from pdftex

git-svn-id: svn://tug.org/texlive/trunk@12900 c570f23f-e606-0410-a88d-b1316a301751

4 files changed, 126 insertions, 40 deletions

diff --git a/Build/source/texk/web2c/pdftexdir/pdftex.web b/Build/source/texk/web2c/pdftexdir/pdftex.web
index 3a241295e4d..b5d49d6cecb 100644
--- a/Build/source/texk/web2c/pdftexdir/pdftex.web
+++ b/Build/source/texk/web2c/pdftexdir/pdftex.web
@@ -288,7 +288,7 @@ known as `\eTeX'.
   {printed when \eTeX\ starts}
 @#
 @d pdftex_version==140 { \.{\\pdftexversion} }
-@d pdftex_revision=="9" { \.{\\pdftexrevision} }
+@d pdftex_revision=="10" { \.{\\pdftexrevision} }
 @d pdftex_version_string=='-1.40.10' {current \pdfTeX\ version}
 @#
 @d pdfeTeX_banner=='This is pdfeTeX, Version 3.1415926',pdftex_version_string,eTeX_version_string
@@ -9427,7 +9427,9 @@ label exit;
 var p:pointer; {tail of the backup list}
 @!q:pointer; {new node being added to the token list via |store_new_token|}
 @!k:pool_pointer; {index into |str_pool|}
+@!save_cur_cs:pointer; {to save |cur_cs|}
 begin p:=backup_head; link(p):=null; k:=str_start[s];
+save_cur_cs:=cur_cs;
 while k<str_start[s+1] do
   begin get_x_token; {recursion is possible here}
 @^recursion@>
@@ -9438,6 +9440,7 @@ while k<str_start[s+1] do
   else if (cur_cmd<>spacer)or(p<>backup_head) then
     begin back_input;
     if p<>backup_head then back_list(link(backup_head));
+    cur_cs:=save_cur_cs;
     scan_keyword:=false; return;
     end;
   end;
@@ -19289,26 +19292,74 @@ if (pdf_unique_resname > 0) and (pdf_resname_prefix = 0) then
 
 @ Finishing the PDF output file.
 
-The following procedures sort the table of destination names
-@p function str_less_str(s1, s2: str_number): boolean; {compare two strings}
-var j1, j2: pool_pointer;
-    l, i: integer;
+The following procedures sort the table of destination names.
+@d get_next_char(#)==
+    c@&# := str_pool[j@&#];
+    incr(j@&#);
+    if (c@&# = 92) and (j@&# < e@&#) then begin
+        c@&# := str_pool[j@&#];
+        incr(j@&#);
+        if (c@&# >= 48) and (c@&# <= 55) then begin
+            c@&# := c@&# - 48;
+            if (j@&# < e@&#) and (str_pool[j@&#] >= 48)
+                         and (str_pool[j@&#] <= 55) then begin
+                c@&# := 8 * c@&# + str_pool[j@&#] - 48;
+                incr(j@&#);
+                if (j@&# < e@&#) and (str_pool[j@&#] >= 48)
+                             and (str_pool[j@&#] <= 55)
+                             and (c@&# < 32) then begin
+                    c@&# := 8 * c@&# + str_pool[j@&#] - 48;
+                    incr(j@&#);
+                end;
+            end;
+        end else begin
+            case c@&# of
+                 98: c@&# :=  8; {`\.b': backspace} 
+                102: c@&# := 12; {`\.f': form feed}
+                110: c@&# := 10; {`\.n': line feed}
+                114: c@&# := 13; {`\.r': carriage return} 
+                116: c@&# :=  9; {`\.t': horizontal tab}
+                {nothing to do for `\.{\\}', `\.(', `\.)'}
+            othercases do_nothing
+            endcases;
+        end;
+    end
+
+@p function str_less_str(s1, s2: str_number): boolean; {compare two pdf strings}
+var j1, j2, e1, e2: pool_pointer;
+    c1, c2: packed_ASCII_code;
 begin
+    {Minimal requirement: output of \.{\\pdfescapestring} must be supported.}
+    {This implementation also supports all escape sequences}
+    {listed in the table `Escape sequences in literal strings'}
+    {of the pdf specification.}
+    {End-of-line markers are not detected:}
+    {The marker is not replaced by `\.{\\n}' or removed if it is escaped.}
     j1 := str_start[s1];
     j2 := str_start[s2];
-    if length(s1) < length(s2) then
-        l := length(s1)
-    else
-        l := length(s2);
-    i := 0;
-    while (i < l) and (str_pool[j1 + i] = str_pool[j2 + i]) do
-        incr(i);
-    if ((i < l) and (str_pool[j1 + i] < str_pool[j2 + i])) or
-        ((i = l) and (length(s1) < length(s2))) then
+    e1 := j1 + length(s1);
+    e2 := j2 + length(s2);
+    while (j1 < e1) and (j2 < e2) do begin
+        {get next character of first string}
+        get_next_char(1);
+        {get next character of second string}
+        get_next_char(2);
+        {compare characters}
+        if c1 < c2 then begin
+            str_less_str := true;
+            return;
+        end
+        else if c1 > c2 then begin
+            str_less_str := false;
+            return;
+        end;
+    end;
+    {compare string lengths}
+    if (j1 >= e1) and (j2 < e2) then
         str_less_str := true
     else
         str_less_str := false;
-end;
+exit: end;
 
 procedure sort_dest_names(l, r: integer); {sorts |dest_names| by names}
 var i, j: integer;
diff --git a/Build/source/texk/web2c/pdftexdir/ptexlib.h b/Build/source/texk/web2c/pdftexdir/ptexlib.h
index 48eac9ae2bf..9c17e3eca4e 100644
--- a/Build/source/texk/web2c/pdftexdir/ptexlib.h
+++ b/Build/source/texk/web2c/pdftexdir/ptexlib.h
@@ -198,7 +198,7 @@ extern boolean handle_subfont_fm(fm_entry *, int);
 /* tounicode.c */
 extern void glyph_unicode_free(void);
 extern void deftounicode(strnumber, strnumber);
-extern integer write_tounicode(char **, char *);
+extern integer write_tounicode(char **, const char *, const char *);
 
 /* utils.c */
 extern boolean str_eq_cstr(strnumber, char *);
diff --git a/Build/source/texk/web2c/pdftexdir/tounicode.c b/Build/source/texk/web2c/pdftexdir/tounicode.c
index 99b7d0fc247..80d52bf79dc 100644
--- a/Build/source/texk/web2c/pdftexdir/tounicode.c
+++ b/Build/source/texk/web2c/pdftexdir/tounicode.c
@@ -124,7 +124,7 @@ void deftounicode(strnumber glyph, strnumber unistr)
 }
 
 
-static long check_unicode_value(char *s, boolean multiple_value)
+static long check_unicode_value(const char *s, boolean multiple_value)
 {
     int l = strlen(s);
     int i;
@@ -181,12 +181,15 @@ static char *utf16be_str(long code)
 }
 
 
-/* this function set proper values to *gp based on s; in case it returns
+/* this function writes /ToUnicode data to *gp based on glyph name s and
+ * taking into account tfmname; in case it returns
  * gp->code == UNI_EXTRA_STRING then the caller is responsible for freeing
  * gp->unicode_seq too */
-static void set_glyph_unicode(char *s, glyph_unicode_entry * gp)
+static void set_glyph_unicode(const char *s, const char* tfmname, 
+                              glyph_unicode_entry *gp)
 {
     char buf[SMALL_BUF_SIZE], buf2[SMALL_BUF_SIZE], *p;
+    const char *p2; /* p2 points in s; p above points in writable copies */
     long code;
     boolean last_component;
     glyph_unicode_entry tmp, *ptmp;
@@ -220,7 +223,7 @@ static void set_glyph_unicode(char *s, glyph_unicode_entry * gp)
         for (;;) {
             *p = 0;
             tmp.code = UNI_UNDEF;
-            set_glyph_unicode(s, &tmp);
+            set_glyph_unicode(s, tfmname, &tmp);
             switch (tmp.code) {
             case UNI_UNDEF:    /* not found, do nothing */
                 break;
@@ -253,8 +256,26 @@ static void set_glyph_unicode(char *s, glyph_unicode_entry * gp)
         return;
     }
 
-    /* lookup for glyph name in the database */
-    tmp.name = s;
+    /* Glyph name search strategy: first look up the glyph name in the
+       tfm's namespace, failing that look it up in the main database. */
+    /* Note: buf may alias s in the code below, but s and buf2 are
+       guaranteed to be distinct because the code changing buf2 above
+       always returns before reaching the code below. */
+
+    /* lookup for glyph name in the tfm's namespace */
+    snprintf(buf2, SMALL_BUF_SIZE, "tfm:%s/%s", tfmname, s);
+    tmp.name = buf2;
+    tmp.code = UNI_UNDEF;
+    ptmp = (glyph_unicode_entry *) avl_find(glyph_unicode_tree, &tmp);
+    if (ptmp != NULL) {
+        gp->code = ptmp->code;
+        gp->unicode_seq = ptmp->unicode_seq;
+        return;
+    }
+
+    /* lookup for glyph name in the main database */
+    tmp.name = (char *)s; /* this is okay since we're not calling
+                             destroy_glyph_unicode_entry on this */
     tmp.code = UNI_UNDEF;
     ptmp = (glyph_unicode_entry *) avl_find(glyph_unicode_tree, &tmp);
     if (ptmp != NULL) {
@@ -265,14 +286,14 @@ static void set_glyph_unicode(char *s, glyph_unicode_entry * gp)
 
     /* check for case of "uniXXXX" (multiple 4-hex-digit values allowed) */
     if (str_prefix(s, "uni")) {
-        p = s + strlen("uni");
-        code = check_unicode_value(p, true);
+        p2 = s + strlen("uni");
+        code = check_unicode_value(p2, true);
         if (code != UNI_UNDEF) {
-            if (strlen(p) == 4) /* single value */
+            if (strlen(p2) == 4) /* single value */
                 gp->code = code;
             else {              /* multiple value */
                 gp->code = UNI_EXTRA_STRING;
-                gp->unicode_seq = xstrdup(p);
+                gp->unicode_seq = xstrdup(p2);
             }
         }
         return;                 /* since the last case cannot happen */
@@ -280,8 +301,8 @@ static void set_glyph_unicode(char *s, glyph_unicode_entry * gp)
 
     /* check for case of "uXXXX" (single value up to 6 hex digits) */
     if (str_prefix(s, "u")) {
-        p = s + strlen("u");
-        code = check_unicode_value(p, false);
+        p2 = s + strlen("u");
+        code = check_unicode_value(p2, false);
         if (code != UNI_UNDEF) {
             assert(code >= 0);
             gp->code = code;
@@ -289,27 +310,41 @@ static void set_glyph_unicode(char *s, glyph_unicode_entry * gp)
     }
 }
 
-integer write_tounicode(char **glyph_names, char *name)
+
+/* tfmname is without .tfm extension, but encname ends in .enc; */
+integer write_tounicode(char **glyph_names, const char *tfmname,
+                        const char* encname)
 {
     char buf[SMALL_BUF_SIZE], *p;
-    static char builtin_suffix[] = "-builtin";
+    static char builtin_suffix[] = "builtin";
     short range_size[257];
     glyph_unicode_entry gtab[257];
     integer objnum;
     int i, j;
     int bfchar_count, bfrange_count, subrange_count;
-    assert(strlen(name) + strlen(builtin_suffix) < SMALL_BUF_SIZE);
+
     if (glyph_unicode_tree == NULL) {
         pdftex_warn("no GlyphToUnicode entry has been inserted yet!");
         fixedgentounicode = 0;
         return 0;
     }
-    strcpy(buf, name);
-    if ((p = strrchr(buf, '.')) != NULL && strcmp(p, ".enc") == 0)
-        *p = 0;                 /* strip ".enc" from encoding name */
-    else
-        strcat(buf, builtin_suffix);    /* ".enc" not present, this is a builtin
-                                           encoding so the name is eg "cmr10-builtin" */
+
+    /* build the name for this CMap as <tfmname>-<encname>; if encname is NULL
+     * then this is a builtin encoding so use instead builtin_suffix */
+    strcpy(buf, tfmname);
+    strcat(buf, "-");
+    if (encname) {
+        assert(strlen(tfmname) + strlen(encname) + 1 < SMALL_BUF_SIZE);
+        strcat(buf, encname);
+        if ((p = strrchr(buf, '.')) != NULL && strcmp(p, ".enc") == 0)
+            *p = 0;                 /* strip ".enc" from encoding name */
+        else /* some silly encoding file name not ending in enc; use as-is */
+            pdftex_warn("Dubious encoding file name: `%s'", encname);
+    } else { /* this is a builtin encoding, so name is e.g. "cmr10-builtin" */
+        assert(strlen(tfmname) + strlen(builtin_suffix) + 1 < SMALL_BUF_SIZE);
+        strcat(buf, builtin_suffix);    
+    }
+
     objnum = pdfnewobjnum();
     pdfbegindict(objnum, 0);
     pdfbeginstream();
@@ -336,7 +371,7 @@ integer write_tounicode(char **glyph_names, char *name)
     /* set gtab */
     for (i = 0; i < 256; ++i) {
         gtab[i].code = UNI_UNDEF;
-        set_glyph_unicode(glyph_names[i], &gtab[i]);
+        set_glyph_unicode(glyph_names[i], tfmname, &gtab[i]);
     }
     gtab[256].code = UNI_UNDEF;
 
diff --git a/Build/source/texk/web2c/pdftexdir/writefont.c b/Build/source/texk/web2c/pdftexdir/writefont.c
index 29fe0b7fb8a..30ed172bad0 100644
--- a/Build/source/texk/web2c/pdftexdir/writefont.c
+++ b/Build/source/texk/web2c/pdftexdir/writefont.c
@@ -531,11 +531,11 @@ void write_fontdictionary(fo_entry * fo)
     if (fixedgentounicode > 0 && fo->fd != NULL) {
         if (fo->fe != NULL) {
             fo->tounicode_objnum =
-                write_tounicode(fo->fe->glyph_names, fo->fe->name);
+                write_tounicode(fo->fe->glyph_names, fo->fm->tfm_name, fo->fe->name);
         } else if (is_type1(fo->fm)) {
             assert(fo->fd->builtin_glyph_names != NULL);
             fo->tounicode_objnum =
-                write_tounicode(fo->fd->builtin_glyph_names, fo->fm->tfm_name);
+                write_tounicode(fo->fd->builtin_glyph_names, fo->fm->tfm_name, NULL);
         }
     }