1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494
|
open Pxp_reader;;
open Pxp_types;;
open Netulex;;
open Minilex;; (* defines [nextchar] *)
let lex_next_iso88591 lsrc =
(* Returns code point of next char, assumes rep_encoding = ISO-8859-1 *)
let lexbuf = Lazy.force lsrc.lsrc_lexbuf in
match nextchar lexbuf with
None -> None
| Some x -> Some(Char.code x)
;;
let lex_next_s lsrc =
(* Returns next char or next partial char as string, encoded in
* rep encoding
*)
let lexbuf = Lazy.force lsrc.lsrc_lexbuf in
match nextchar lexbuf with
None -> ""
| Some x -> String.make 1 x
;;
let ulex_next lsrc =
(* Returns code point of next char *)
let ulb = Lazy.force lsrc.lsrc_unicode_lexbuf in
try
if ulb.ULB.ulb_chars_len = 0 then
ULB.refill ulb; (* may raise End_of_file *)
assert(ulb.ULB.ulb_chars_len > 0);
let code = ulb.ULB.ulb_chars.(0) in
(* print_endline (" CODE: " ^ string_of_int code); *)
ULB.delete 1 ulb;
Some code
with
End_of_file -> (* print_endline " EOF"; *) None
;;
let ulex_next_s lsrc =
(* Returns next char as UTF-8 string *)
let ulb = Lazy.force lsrc.lsrc_unicode_lexbuf in
try
if ulb.ULB.ulb_chars_len = 0 then
ULB.refill ulb; (* may raise End_of_file *)
assert(ulb.ULB.ulb_chars_len > 0);
let s = ULB.utf8_sub_string 0 1 ulb in
ULB.delete 1 ulb;
(*
for i = 0 to String.length s - 1 do
print_string (string_of_int (Char.code s.[i]) ^ " ");
done;
print_endline "";
*)
s
with
End_of_file -> (* print_endline "EOF"; *) ""
;;
let make_channel s =
(* Returns a channel reading the bytes from the string s *)
let rd, wr = Unix.pipe() in
let ch_rd = Unix.in_channel_of_descr rd in
let ch_wr = Unix.out_channel_of_descr wr in
ignore
(Thread.create
(fun () ->
output_string ch_wr s;
close_out ch_wr;
)
()
);
ch_rd
;;
(**********************************************************************)
let t001 next () =
(* Reads from a string (without recoding it), checks the lexbuf size *)
let s = "0123456789abc" in
let r = new resolve_read_this_string s in
r # init_rep_encoding `Enc_iso88591;
r # init_warner None (new drop_warnings);
let lsrc = r # open_in Anonymous in
let c = next lsrc in
assert (c = Some(Char.code '0'));
ignore(next lsrc);
ignore(next lsrc);
ignore(next lsrc);
ignore(next lsrc);
ignore(next lsrc);
ignore(next lsrc);
ignore(next lsrc);
ignore(next lsrc);
let c = next lsrc in
assert (c = Some(Char.code '9'));
r # change_encoding "";
let c = next lsrc in
assert (c = Some(Char.code 'a'));
ignore(next lsrc);
let c = next lsrc in
assert (c = Some(Char.code 'c'));
let c = next lsrc in
assert (c = None);
r # close_in;
true
;;
let t002 next () =
(* Like t001, but reads from a channel *)
let ch = make_channel "0123456789abc" in
let r = new resolve_read_this_channel ch in
r # init_rep_encoding `Enc_iso88591;
r # init_warner None (new drop_warnings);
let lsrc = r # open_in Anonymous in
let c = next lsrc in
assert (c = Some(Char.code '0'));
ignore(next lsrc);
ignore(next lsrc);
ignore(next lsrc);
ignore(next lsrc);
ignore(next lsrc);
ignore(next lsrc);
ignore(next lsrc);
ignore(next lsrc);
let c = next lsrc in
assert (c = Some(Char.code '9'));
r # change_encoding "";
let c = next lsrc in
assert (c = Some(Char.code 'a'));
ignore(next lsrc);
let c = next lsrc in
assert (c = Some(Char.code 'c'));
let c = next lsrc in
assert (c = None);
r # close_in;
true
;;
let t003 next_s () =
(* Tests non-automatic encoding conversion from ISO-8859-1 to UTF-8 *)
let s = "0硿" in
let r = new resolve_read_this_string ~fixenc:`Enc_iso88591 s in
r # init_rep_encoding `Enc_utf8;
r # init_warner None (new drop_warnings);
let lsrc = r # open_in Anonymous in
let c = ref (next_s lsrc) in
assert (!c = "0");
let u = ref "" in
while !c <> "" do
u := !u ^ !c;
c := next_s lsrc
done;
r # close_in;
!u = "0\194\171\194\187\194\176\195\161\195\160\195\162\195\163\195\164\195\129\195\128\195\130\195\131\195\132\195\169\195\168\195\170\195\171\195\173\195\172\195\174\195\175\195\141\195\140\195\142\195\143\195\179\195\178\195\180\195\181\195\184\195\182\195\147\195\146\195\148\195\149\195\152\195\150\195\186\195\185\195\187\195\188\195\189\195\191\195\157\195\159\195\167\194\161\194\191\195\177\195\145"
;;
let t004 next () =
(* Tests non-automatic encoding conversion from UTF-8 to ISO-8859-1 *)
let s = "0\194\171\194\187\194\176\195\161\195\160\195\162\195\163\195\164\195\129\195\128\195\130\195\131\195\132\195\169\195\168\195\170\195\171\195\173\195\172\195\174\195\175\195\141\195\140\195\142\195\143\195\179\195\178\195\180\195\181\195\184\195\182\195\147\195\146\195\148\195\149\195\152\195\150\195\186\195\185\195\187\195\188\195\189\195\191\195\157\195\159\195\167\194\161\194\191\195\177\195\145" in
let r = new resolve_read_this_string ~fixenc:`Enc_utf8 s in
r # init_rep_encoding `Enc_iso88591;
r # init_warner None (new drop_warnings);
let lsrc = r # open_in Anonymous in
let c = ref (next lsrc) in
assert (!c = Some(Char.code '0'));
let u = ref "" in
while !c <> None do
( match !c with
Some x -> u := !u ^ String.make 1 (Char.chr x)
| None -> assert false
);
c := next lsrc
done;
r # close_in;
!u = "0硿"
;;
let t005 next () =
(* Tests automatic encoding conversion from UTF-8 to ISO-8859-1 *)
let s = "0\194\171\194\187\194\176\195\161\195\160\195\162\195\163\195\164\195\129\195\128\195\130\195\131\195\132\195\169\195\168\195\170\195\171\195\173\195\172\195\174\195\175\195\141\195\140\195\142\195\143\195\179\195\178\195\180\195\181\195\184\195\182\195\147\195\146\195\148\195\149\195\152\195\150\195\186\195\185\195\187\195\188\195\189\195\191\195\157\195\159\195\167\194\161\194\191\195\177\195\145" in
let r = new resolve_read_this_string s in
r # init_rep_encoding `Enc_iso88591;
r # init_warner None (new drop_warnings);
let lsrc = r # open_in Anonymous in
let c = ref (next lsrc) in
assert (!c = Some(Char.code '0'));
let u = ref "" in
while !c <> None do
( match !c with
Some x -> assert(x <= 255); u := !u ^ String.make 1 (Char.chr x)
| None -> ()
);
c := next lsrc
done;
r # close_in;
!u = "0硿"
;;
let t006 next_s () =
(* Tests automatic encoding conversion from UTF-16-BE to UTF-8
* This variant invokes change_encoding early.
*)
let s = "\254\255\0000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000" in
let r = new resolve_read_this_string s in
r # init_rep_encoding `Enc_utf8;
r # init_warner None (new drop_warnings);
let lsrc = r # open_in Anonymous in
let c = ref (next_s lsrc) in
assert (!c = "0");
r # change_encoding "";
let u = ref "" in
while !c <> "" do
u := !u ^ !c;
c := next_s lsrc
done;
r # close_in;
!u = "0\194\171\194\187\194\176\195\161\195\160\195\162\195\163\195\164\195\129\195\128\195\130\195\131\195\132\195\169\195\168\195\170\195\171\195\173\195\172\195\174\195\175\195\141\195\140\195\142\195\143\195\179\195\178\195\180\195\181\195\184\195\182\195\147\195\146\195\148\195\149\195\152\195\150\195\186\195\185\195\187\195\188\195\189\195\191\195\157\195\159\195\167\194\161\194\191\195\177\195\145"
;;
let t007 next_s () =
(* Tests automatic encoding conversion from UTF-16-BE to UTF-8
* This variant does not invoke change_encoding
*)
let s = "\254\255\0000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000" in
let r = new resolve_read_this_string s in
r # init_rep_encoding `Enc_utf8;
r # init_warner None (new drop_warnings);
let lsrc = r # open_in Anonymous in
let c = ref (next_s lsrc) in
assert (!c = "0");
let u = ref "" in
while !c <> "" do
u := !u ^ !c;
c := next_s lsrc
done;
r # close_in;
!u = "0\194\171\194\187\194\176\195\161\195\160\195\162\195\163\195\164\195\129\195\128\195\130\195\131\195\132\195\169\195\168\195\170\195\171\195\173\195\172\195\174\195\175\195\141\195\140\195\142\195\143\195\179\195\178\195\180\195\181\195\184\195\182\195\147\195\146\195\148\195\149\195\152\195\150\195\186\195\185\195\187\195\188\195\189\195\191\195\157\195\159\195\167\194\161\194\191\195\177\195\145"
;;
let t008 next_s () =
(* Invokes change_encoding in the middle *)
let s = "0\194\171" in
let r = new resolve_read_this_string s in
r # init_rep_encoding `Enc_utf8;
r # init_warner None (new drop_warnings);
let lsrc = r # open_in Anonymous in
assert(next_s lsrc = "0");
let u = ref "" in
while String.length !u < 2 do
let s = next_s lsrc in
assert(s <> "");
u := !u ^ s
done;
assert(!u = "\194\171"); (* Must be UTF-8 *)
r # change_encoding "ISO-8859-1";
u := "";
while String.length !u < 2 do
let s = next_s lsrc in
assert(s <> "");
u := !u ^ s
done;
assert(!u = "\194\171"); (* Must be UTF-8 *)
true
;;
(**********************************************************************)
let t100 next_s () =
(* Reads from a file without recoding it *)
let r = new resolve_as_file () in
r # init_rep_encoding `Enc_utf8;
r # init_warner None (new drop_warnings);
let cwd = Sys.getcwd() in
let lsrc = r # open_in (System ("file://localhost" ^ cwd ^ "/t100.dat")) in
let c = next_s lsrc in
assert (c = "0");
for i = 1 to 8 do
ignore(next_s lsrc);
done;
let c = next_s lsrc in
assert (c = "9");
r # close_in;
true
;;
let t101 next_s () =
(* Reads from a file without recoding it *)
let r = new resolve_as_file ~base_url_defaults_to_cwd:true () in
r # init_rep_encoding `Enc_utf8;
r # init_warner None (new drop_warnings);
let cwd = Sys.getcwd() in
let lsrc = r # open_in (System ("//localhost" ^ cwd ^ "/t100.dat")) in
let c = next_s lsrc in
assert (c = "0");
for i = 1 to 8 do
ignore(next_s lsrc);
done;
let c = next_s lsrc in
assert (c = "9");
r # close_in;
true
;;
let t102 next_s () =
(* Reads from a file without recoding it *)
let r = new resolve_as_file ~base_url_defaults_to_cwd:true () in
r # init_rep_encoding `Enc_utf8;
r # init_warner None (new drop_warnings);
let cwd = Sys.getcwd() in
let lsrc = r # open_in (System (cwd ^ "/t100.dat")) in
let c = next_s lsrc in
assert (c = "0");
for i = 1 to 8 do
ignore(next_s lsrc);
done;
let c = next_s lsrc in
assert (c = "9");
r # close_in;
true
;;
let t103 next_s () =
(* Reads from a file without recoding it *)
let r = new resolve_as_file ~base_url_defaults_to_cwd:true () in
r # init_rep_encoding `Enc_utf8;
r # init_warner None (new drop_warnings);
let lsrc = r # open_in (System "t100.dat") in
let c = next_s lsrc in
assert (c = "0");
for i = 1 to 8 do
ignore(next_s lsrc);
done;
let c = next_s lsrc in
assert (c = "9");
r # close_in;
true
;;
(**********************************************************************)
let t110 () =
(* Checks whether relative URLs are properly handled *)
(* Note: Not tested for unicode_lexbuf, no need for that. *)
let r = new resolve_as_file ~base_url_defaults_to_cwd:true () in
r # init_rep_encoding `Enc_utf8;
r # init_warner None (new drop_warnings);
let lsrc = r # open_in (System "t100.dat") in
let lb = Lazy.force lsrc.lsrc_lexbuf in
let c = nextchar lb in
assert (c = Some '0');
for i = 1 to 8 do
ignore(nextchar lb);
done;
let r' = r # clone in
let lsrc' = r' # open_in (System "t100.dat") in
let lb' = Lazy.force lsrc'.lsrc_lexbuf in
let c = nextchar lb' in
assert (c = Some '0');
for i = 1 to 8 do
ignore(nextchar lb');
done;
let c = nextchar lb' in
assert (c = Some '9');
r' # close_in;
let c = nextchar lb in
assert (c = Some '9');
r # close_in;
true
;;
(**********************************************************************)
(* Tests whether the encoding handling of System IDs is okay *)
let t200 () =
(* Check the technique for the following tests:
* [Checks also 'combine' to some extent.)
*)
let r1 = new resolve_read_this_string
~id:(System "b.xml")
~fixenc:`Enc_iso88591
"ae" in
let r2 = new resolve_read_this_string
~id:(System "a.xml")
~fixenc:`Enc_iso88591
"<!DOCTYPE a [ <!ELEMENT a ANY> <!ENTITY ae SYSTEM 'b.xml'> ]> <a>&ae;</a>" in
let r = new combine [ r1; r2 ] in
(* It should now be possible to resolve &ae; *)
let _ =
Pxp_yacc.parse_document_entity
{ Pxp_yacc.default_config with Pxp_yacc.encoding = `Enc_iso88591 }
(Pxp_yacc.ExtID(System "a.xml", r))
Pxp_yacc.default_spec
in
true
;;
let t201 () =
(* Check that System IDs are converted to UTF-8. rep_encoding = ISO-8859-1 *)
let r1 = new resolve_read_this_string
~id:(System "\195\164.xml") (* This is an UTF-8 ""! *)
~fixenc:`Enc_iso88591
"ae" in
let r2 = new resolve_read_this_string
~id:(System "a.xml")
~fixenc:`Enc_iso88591
"<!DOCTYPE a [ <!ELEMENT a ANY> <!ENTITY ae SYSTEM '.xml'> ]> <a>&ae;</a>" in
let r = new combine [ r1; r2 ] in
(* It should now be possible to resolve &ae; *)
let _ =
Pxp_yacc.parse_document_entity
{ Pxp_yacc.default_config with Pxp_yacc.encoding = `Enc_iso88591 }
(Pxp_yacc.ExtID(System "a.xml", r))
Pxp_yacc.default_spec
in
true
;;
let t202 () =
(* Check that System IDs are converted to UTF-8. rep_encoding = UTF-8 *)
let r1 = new resolve_read_this_string
~id:(System "\195\164.xml")
~fixenc:`Enc_iso88591
"ae" in
let r2 = new resolve_read_this_string
~id:(System "a.xml")
~fixenc:`Enc_iso88591
"<!DOCTYPE a [ <!ELEMENT a ANY> <!ENTITY ae SYSTEM '.xml'> ]> <a>&ae;</a>" in
let r = new combine [ r1; r2 ] in
(* It should now be possible to resolve &ae; *)
let _ =
Pxp_yacc.parse_document_entity
{ Pxp_yacc.default_config with Pxp_yacc.encoding = `Enc_utf8 }
(Pxp_yacc.ExtID(System "a.xml", r))
Pxp_yacc.default_spec
in
true
;;
(**********************************************************************)
let test f n =
try
print_string ("Reader test " ^ n);
flush stdout;
if f() then
print_endline " ok"
else
print_endline " FAILED!!!!";
with
error ->
print_endline (" FAILED: " ^ string_of_exn error)
;;
test (t001 lex_next_iso88591) "001 lex";;
test (t001 ulex_next) "001 ulex";;
test (t002 lex_next_iso88591) "002 lex";;
test (t002 ulex_next) "002 ulex";;
test (t003 lex_next_s) "003 lex";;
test (t003 ulex_next_s) "003 ulex";;
test (t004 lex_next_iso88591) "004 lex";;
test (t004 ulex_next) "004 ulex";;
test (t005 lex_next_iso88591) "005 lex";;
test (t005 ulex_next) "005 ulex";;
test (t006 lex_next_s) "006 lex";;
test (t006 ulex_next_s) "006 ulex";;
test (t007 lex_next_s) "007 lex";;
test (t007 ulex_next_s) "007 ulex";;
test (t008 lex_next_s) "008 lex";;
test (t008 ulex_next_s) "008 ulex";;
test (t100 lex_next_s) "100 lex";;
test (t100 ulex_next_s) "100 ulex";;
test (t101 lex_next_s) "101 lex";;
test (t101 ulex_next_s) "101 ulex";;
test (t102 lex_next_s) "102 lex";;
test (t102 ulex_next_s) "102 ulex";;
test (t103 lex_next_s) "103 lex";;
test (t103 ulex_next_s) "103 ulex";;
test t110 "110";;
test t200 "200";;
test t201 "201";;
test t202 "202";;
|