⟦9a58317c4⟧

TextFile

*** ctex.ch	Mon Mar 18 10:42:57 1991
--- bigtrie.ch	Tue Mar 19 15:55:56 1991
***************
*** 43,45 ****
  %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
! % [1.2] banner
  %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
--- 43,45 ----
  %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
! % [1.2] banner (changed to show trie extension version)
  %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
***************
*** 48,50 ****
  @y
! @d banner=='This is TeX, C Version 3.14' {printed when \TeX\ starts}
  @z
--- 48,50 ----
  @y
! @d banner=='This is TeX, C Version 3.14t3' {printed when \TeX\ starts}
  @z
***************
*** 176,178 ****
  @<Constants...@>=
! @!mem_max=65530; {greatest index in \TeX's internal |mem| array;
    must be strictly less than |max_halfword|;
--- 176,178 ----
  @<Constants...@>=
! @!mem_max=262140; {greatest index in \TeX's internal |mem| array;
    must be strictly less than |max_halfword|;
***************
*** 182,184 ****
    must be equal to |mem_bot| in \.{INITEX}, otherwise |<=mem_bot|}
! @!buf_size=2000; {maximum number of characters simultaneously present in
    current lines of open files and in control sequences between
--- 182,184 ----
    must be equal to |mem_bot| in \.{INITEX}, otherwise |<=mem_bot|}
! @!buf_size=3000; {maximum number of characters simultaneously present in
    current lines of open files and in control sequences between
***************
*** 189,191 ****
  @!max_print_line=79; {width of longest text lines output; should be at least 60}
! @!stack_size=200; {maximum number of simultaneous input sources}
  @!max_in_open=15; {maximum number of input files and error insertions that
--- 189,191 ----
  @!max_print_line=79; {width of longest text lines output; should be at least 60}
! @!stack_size=300; {maximum number of simultaneous input sources}
  @!max_in_open=15; {maximum number of input files and error insertions that
***************
*** 192,196 ****
    can be going on simultaneously}
! @!font_max=120; {maximum internal font number; must not exceed |max_quarterword|
    and must be at most |font_base+256|}
! @!font_mem_size=36000; {number of words of |font_info| for all fonts}
  @!param_size=60; {maximum number of simultaneous macro parameters}
--- 192,196 ----
    can be going on simultaneously}
! @!font_max=255; {maximum internal font number; must not exceed |max_quarterword|
    and must be at most |font_base+256|}
! @!font_mem_size=72000; {number of words of |font_info| for all fonts}
  @!param_size=60; {maximum number of simultaneous macro parameters}
***************
*** 197,200 ****
  @!nest_size=40; {maximum number of semantic levels simultaneously active}
! @!max_strings=4400; {maximum number of strings; must not exceed |max_halfword|}
! @!string_vacancies=15000; {the minimum number of characters that should be
    available for the user's control sequences and font names,
--- 197,200 ----
  @!nest_size=40; {maximum number of semantic levels simultaneously active}
! @!max_strings=7500; {maximum number of strings; must not exceed |max_halfword|}
! @!string_vacancies=74000; {the minimum number of characters that should be
    available for the user's control sequences and font names,
***************
*** 201,203 ****
    after \TeX's own error messages are stored}
! @!pool_size=45000; {maximum number of characters in strings, including all
    error messages and help texts, and the names of all fonts and
--- 201,203 ----
    after \TeX's own error messages are stored}
! @!pool_size=100000; {maximum number of characters in strings, including all
    error messages and help texts, and the names of all fonts and
***************
*** 205,212 ****
    length of \TeX's own strings, which is currently about 23000}
! @!save_size=2000; {space for saving values outside of current group; must be
    at most |max_halfword|}
! @!trie_size=8000; {space for hyphenation patterns; should be larger for
    \.{INITEX} than it is in production versions of \TeX}
! @!trie_op_size=500; {space for ``opcodes'' in the hyphenation patterns}
! @!neg_trie_op_size=-500; {for lower trie_op_hash array bound}
  @!dvi_buf_size=16384; {size of the output buffer; must be a multiple of 8}
--- 205,214 ----
    length of \TeX's own strings, which is currently about 23000}
! @!save_size=4000; {space for saving values outside of current group; must be
    at most |max_halfword|}
! @!trie_size=24000; {space for hyphenation patterns; should be larger for
    \.{INITEX} than it is in production versions of \TeX}
! @!trie_op_size=750; {space for ``opcodes'' in the hyphenation patterns}
! @!neg_trie_op_size=-750; {for lower trie_op_hash array bound}
! @!min_trie_op=0; {first possible trie op code for any language}
! @!max_trie_op=500; {largest possible trie op code for any language}
  @!dvi_buf_size=16384; {size of the output buffer; must be a multiple of 8}
***************
*** 214,216 ****
    {string of length |file_name_size|; tells where the string pool appears}
! @!mem_top=65530; {largest index in the |mem| array dumped by \.{INITEX};
    must be substantially larger than |mem_bot|
--- 216,218 ----
    {string of length |file_name_size|; tells where the string pool appears}
! @!mem_top=262140; {largest index in the |mem| array dumped by \.{INITEX};
    must be substantially larger than |mem_bot|
***************
*** 238,239 ****
--- 240,242 ----
  @d hash_prime=1777 {a prime number equal to about 85\pct! of |hash_size|}
+ @d hyph_size=307 {another prime; the number of \.{\\hyphenation} exceptions}
  @y
***************
*** 243,247 ****
    than |min_quarterword|}
! @d hash_size=3000 {maximum number of control sequences; it should be at most
    about |(mem_max-mem_min)/10|}
! @d hash_prime=2551 {a prime number equal to about 85\pct! of |hash_size|}
  @z
--- 246,251 ----
    than |min_quarterword|}
! @d hash_size=9500 {maximum number of control sequences; it should be at most
    about |(mem_max-mem_min)/10|}
! @d hash_prime=7919 {a prime number equal to about 85\pct! of |hash_size|}
! @d hyph_size=607 {another prime; the number of \.{\\hyphenation} exceptions}
  @z
***************
*** 703,705 ****
  @d min_halfword==0 {smallest allowable value in a |halfword|}
! @d max_halfword==65535 {largest allowable value in a |halfword|}
  @z
--- 707,709 ----
  @d min_halfword==0 {smallest allowable value in a |halfword|}
! @d max_halfword==262143 {largest allowable value in a |halfword|}
  @z
***************
*** 1167,1168 ****
--- 1171,1256 ----
  %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+ % [42.920,921,923,924] Allow larger hyphenation tries.
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+ @x
+ Comparatively few different number sequences $n_0\ldots n_k$ actually occur,
+ since most of the |n|'s are generally zero. Therefore the number sequences
+ are encoded in such a way that |trie_op|$(z_k)$ is only one byte long.
+ If |trie_op(@t$z_k$@>)<>min_quarterword|, when $p_1\ldots p_k$ has matched
+ the letters in |hc[(l-k+1)..l@,]| of language |t|,
+ we perform all of the required operations
+ for this pattern by carrying out the following little program: Set
+ |v:=trie_op(@t$z_k$@>)|. Then set |v:=v+op_start[t]|,
+ |hyf[l-hyf_distance[v]]:=@tmax@>(hyf[l-hyf_distance[v]], hyf_num[v])|,
+ and |v:=hyf_next[v]|; repeat, if necessary, until |v=min_quarterword|.
+ @y
+ The theory that comparatively few different number sequences $n_0\ldots n_k$
+ actually occur, since most of the |n|'s are generally zero, seems to fail
+ at least for the large German hyphenation patterns.
+ Therefore the number sequences cannot any longer be encoded in such a way
+ that |trie_op|$(z_k)$ is only one byte long.
+ We have introduced a new constant |max_trie_op| for the maximum allowable
+ hyphenation operation code value; |max_trie_op| might be different for
+ \TeX\ and \.{INITEX} and must not exceed |max_halfword|.
+ An opcode will occupy a halfword if |max_trie_op| exceeds |max_quarterword|
+ or a quarterword otherwise.
+ @^system dependencies@>
+ If |trie_op(@t$z_k$@>)<>min_trie_op|, when $p_1\ldots p_k$ has matched
+ the letters in |hc[(l-k+1)..l@,]| of language |t|,
+ we perform all of the required operations
+ for this pattern by carrying out the following little program: Set
+ |v:=trie_op(@t$z_k$@>)|. Then set |v:=v+op_start[t]|,
+ |hyf[l-hyf_distance[v]]:=@tmax@>(hyf[l-hyf_distance[v]], hyf_num[v])|,
+ and |v:=hyf_next[v]|; repeat, if necessary, until |v=min_trie_op|.
+ @z
+ @x
+ @!trie_pointer=0..trie_size; {an index into |trie|}
+ @y
+ @!trie_opcode=min_trie_op..max_trie_op;  {a trie opcode}
+ @!trie_pointer=0..trie_size; {an index into |trie|}
+ @z
+ @x
+ @ @d trie_link(#)==trie[#].rh {``downward'' link in a trie}
+ @d trie_char(#)==trie[#].b1 {character matched at this trie location}
+ @d trie_op(#)==trie[#].b0 {program for hyphenation at this trie location}
+ @y
+ @ For more than 255 trie op codes, the three fields |trie_link|, |trie_char|,
+ and |trie_op| will no longer fit into one memory word; thus using web2c
+ we define |trie| as three array instead of an array of records.
+ The variant will be implented by reusing the opcode field later on with
+ another macro.
+ @d trie_link(#)==trie_trl[#] {``downward'' link in a trie}
+ @d trie_char(#)==trie_trc[#] {character matched at this trie location}
+ @d trie_op(#)==trie_tro[#] {program for hyphenation at this trie location}
+ @z
+ @x
+ @!trie:array[trie_pointer] of two_halves; {|trie_link|, |trie_char|, |trie_op|}
+ @y
+ @!trie_trl:array[trie_pointer] of halfword; {|trie_link|}
+ @!trie_tro:array[trie_pointer] of halfword; {|trie_op| and |trie_link|}
+ @!trie_trc:array[trie_pointer] of quarterword; {|trie_char|}
+ @z
+ @x
+     begin if trie_op(z)<>min_quarterword then
+ @y
+     begin if trie_op(z)<>min_trie_op then
+ @z
+ @x
+ until v=min_quarterword;
+ @y
+ until v=min_trie_op;
+ @z
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+ % [43.943] Larger tries, also in documentation parts.
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+ @x
+ |hyf_next[@t$v^\prime$@>]=min_quarterword|.
+ @y
+ |hyf_next[@t$v^\prime$@>]=min_trie_op|.
+ @z
+ @x
+ $$\hbox{|@t$v^\prime$@>:=new_trie_op(0,1,min_quarterword)|,\qquad
+ @y
+ $$\hbox{|@t$v^\prime$@>:=new_trie_op(0,1,min_trie_op)|,\qquad
+ @z
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
  % [43.?] Hack around the negative lower bound here.
***************
*** 1183,1188 ****
--- 1271,1307 ----
  
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+ % [43.943,944] Larger hyphenation tries.
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+ @x
+ @!trie_used:array[ASCII_code] of quarterword;
+ @y
+ @!trie_used:array[ASCII_code] of trie_opcode;
+ @z
+ @x
+ @!trie_op_val:array[1..trie_op_size] of quarterword;
+ @y
+ @!trie_op_val:array[1..trie_op_size] of trie_opcode;
+ @z
+ @x
+ tini
+ @y
+ tini@;
+ @!max_op_used:trie_opcode; {largest opcode used for any language}
+ @!small_op:boolean; {flag used while dumping or undumping}
+ @z
+ @x
+ |new_trie_op| could return |min_quarterword| (thereby simply ignoring
+ @y
+ |new_trie_op| could return |min_trie_op| (thereby simply ignoring
+ @z
  @x
+ function new_trie_op(@!d,@!n:small_number;@!v:quarterword):quarterword;
+ label exit;
  var h:-trie_op_size..trie_op_size; {trial hash location}
+ @!u:quarterword; {trial op code}
  @y
+ function new_trie_op(@!d,@!n:small_number;@!v:trie_opcode):trie_opcode;
+ label exit;
  var h:neg_trie_op_size..trie_op_size; {trial hash location}
+ @!u:trie_opcode; {trial op code}
  @z
***************
*** 1200,1201 ****
--- 1319,1356 ----
  %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+ % [43.944,945,946] And larger tries again.
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+ @x
+     if u=max_quarterword then
+       overflow("pattern memory ops per language",
+         max_quarterword-min_quarterword);
+     incr(trie_op_ptr); incr(u); trie_used[cur_lang]:=u;
+ @y
+     if u=max_trie_op then
+       overflow("pattern memory ops per language",
+       max_trie_op-min_trie_op);
+     incr(trie_op_ptr); incr(u); trie_used[cur_lang]:=u;
+     if u>max_op_used then max_op_used:=u;
+ @z
+ @x
+ op_start[0]:=-min_quarterword;
+ @y
+ op_start[0]:=-min_trie_op;
+ @z
+ @x
+ for k:=0 to 255 do trie_used[k]:=min_quarterword;
+ @y
+ for k:=0 to 255 do trie_used[k]:=min_trie_op;
+ @z
+ @x
+ trie_op_ptr:=0;
+ @y
+ max_op_used:=min_trie_op;
+ trie_op_ptr:=0;
+ @z
+ @x
+ @t\hskip10pt@>@!trie_o:packed array[trie_pointer] of quarterword;
+ @y
+ @t\hskip10pt@>@!trie_o:packed array[trie_pointer] of trie_opcode;
+ @z
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
  % [43.947] And another.
***************
*** 1211,1212 ****
--- 1366,1420 ----
  %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+ % [43.950,958,960,963] Larger tries.
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+ @x
+ @d trie_back(#)==trie[#].lh {backward links in |trie| holes}
+ @y
+ @d trie_back(#)==trie_tro[#] {use the opcode field now for backward links}
+ @z
+ @x
+ @<Move the data into |trie|@>=
+ h.rh:=0; h.b0:=min_quarterword; h.b1:=min_quarterword; {|trie_link:=0|,
+   |trie_op:=min_quarterword|, |trie_char:=qi(0)|}
+ if trie_root=0 then {no patterns were given}
+   begin for r:=0 to 256 do trie[r]:=h;
+ @y
+ @d clear_trie == {clear |trie[r]|}
+   begin trie_link(r):=0;
+   trie_op(r):=min_trie_op;
+   trie_char(r):=min_quarterword; {|trie_char:=qi(0)|}
+   end
+ @<Move the data into |trie|@>=
+ if trie_root=0 then {no patterns were given}
+   begin for r:=0 to 256 do clear_trie;
+ @z
+ @x
+   repeat s:=trie_link(r); trie[r]:=h; r:=s;
+ @y
+   repeat s:=trie_link(r); clear_trie; r:=s;
+ @z
+ @x
+ @!v:quarterword; {trie op code}
+ @y
+ @!v:trie_opcode; {trie op code}
+ @z
+ @x
+ if trie_o[q]<>min_quarterword then
+ @y
+ if trie_o[q]<>min_trie_op then
+ @z
+ @x
+ trie_c[p]:=si(c); trie_o[p]:=min_quarterword;
+ @y
+ trie_c[p]:=si(c); trie_o[p]:=min_trie_op;
+ @z
+ @x
+ l:=k; v:=min_quarterword;
+ @y
+ l:=k; v:=min_trie_op;
+ @z
+ @x
+ @!h:two_halves; {template used to zero out |trie|'s holes}
+ @y
+ @z
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
  % [49.1275] Same stuff as for \input, this time for \openin.
***************
*** 1555,1557 ****
  @y
! dump_things(trie[0], trie_max+1);
  dump_int(trie_op_ptr);
--- 1763,1767 ----
  @y
! dump_things(trie_trl[0], trie_max+1);
! dump_things(trie_tro[0], trie_max+1);
! dump_things(trie_trc[0], trie_max+1);
  dump_int(trie_op_ptr);
***************
*** 1571,1573 ****
  @y
! undump_things(trie[0], j+1);
  undump_size(0)(trie_op_size)('trie op size')(j); @+init trie_op_ptr:=j;@+tini
--- 1781,1785 ----
  @y
! undump_things(trie_trl[0], j+1);
! undump_things(trie_tro[0], j+1);
! undump_things(trie_trc[0], j+1);
  undump_size(0)(trie_op_size)('trie op size')(j); @+init trie_op_ptr:=j;@+tini
DataMuseum.dk

DKUUG/EUUG Conference tapes

⟦9a58317c4⟧ TextFile

Derivation

TextFile
