WiktionaryDumps to words: Difference between revisions
m
→{{header|Wren}}: Minor tidy and rerun
m (→{{header|Phix}}: oops, just mullered the tag) |
m (→{{header|Wren}}: Minor tidy and rerun) |
||
| (6 intermediate revisions by 4 users not shown) | |||
Line 4:
Make a file that can be useful with [https://en.wikipedia.org/wiki/Spell_checker spell checkers] like [https://fr.wikipedia.org/wiki/Ispell Ispell] and [https://en.wikipedia.org/wiki/GNU_Aspell Aspell].
Use the [https://dumps.wikimedia.org/enwiktionary/latest/enwiktionary-latest-pages-articles.xml.bz2 wiktionary dump] (input) to create a file equivalent
=={{header|C}}==
<
#include <stdlib.h>
#include <stdbool.h>
Line 205:
return 0;
}</
{{out}}
Line 229:
=={{header|Java}}==
<
import org.xml.sax.helpers.DefaultHandler;
import org.xml.sax.SAXException;
Line 288:
}
}
}</
{{out}}
Line 311:
=={{header|Julia}}==
Uses Regex and a state variable instead of XML parsing. Default setting prints the first 80 French words found.
<
function getwords(io::IO, output::IO; languagemark = "==French==", maxwords = 80)
Line 341:
getwords(stream, stdout) # or open a file to write to and use its IO handle instead of stdout
</
<pre>
gratis
Line 430:
Using the library [http://erratique.ch/software/xmlm xmlm]:
<
let i = Xmlm.make_input ~strip:true (`Channel stdin) in
let title = ref "" in
Line 463:
then print_endline !title
end
done</
{{out}}
Line 481:
minute
...
</pre>
=={{header|Perl}}==
{{trans|Raku}}
<syntaxhighlight lang="perl"># 20211214 Perl programming solution
use strict;
use warnings;
use LWP::UserAgent;
use Compress::Raw::Bzip2 ;
my $LanguageMark = "==French==";
my $Target = 5; # words
my $URL = 'https://dumps.wikimedia.org/enwiktionary/latest/enwiktionary-latest-pages-articles.xml.bz2';
my %needles; my $plain = my $tail = '';
my $ua = LWP::UserAgent->new;
my $bz = new Compress::Raw::Bunzip2({ -Bufsize => 1, -AppendOutput => 0 });
my $res = $ua->request( HTTP::Request->new(GET => $URL),
sub { # @_ = Data Chunk, HTTP::Response
foreach (split '', $_[0]) {
my $status = $bz->bzinflate($_, substr($plain, 0)) ;
last if $status == BZ_STREAM_END or $status != BZ_OK ;
}
if ( scalar ( my @haystacks = split "\n", $plain)) {
$haystacks[0] = $tail . $haystacks[0];
$tail = $haystacks[$#haystacks];
my ($title,$got_text_last) = '', 0 ;
foreach ( @haystacks[0..$#haystacks-1] ) {
if ( /<title>(\w+?)<\/title>/ ) {
($title,$got_text_last) = $1, 0;
} elsif ( /<text/ ) {
$got_text_last = 1;
} elsif ( /$LanguageMark/ ) {
$needles{$title}++ if ( $got_text_last and $title.defined );
if ( %needles >= $Target ) {
print "$_\n" for sort keys %needles;
exit;
}
$got_text_last = 0;
} elsif ( /<\/text>/ ) { $got_text_last = 0 }
}
}
}
)</syntaxhighlight>
{{out}}
<pre>
chien
gratis
gratuit
livre
pond
</pre>
Line 486 ⟶ 542:
Does not rely on wget/bzcat etc. Downloads in 16K or so blocks, unpacks one block at a time in memory, terminates properly when 5 or more words are found.<br>
Tested on Windows, should be fine on Linux as long as you can provide a suitable bz2.so
<!--<
<span style="color: #008080;">constant</span> <span style="color: #000000;">url</span> <span style="color: #0000FF;">=</span> <span style="color: #008000;">"https://dumps.wikimedia.org/enwiktionary/latest/enwiktionary-latest-pages-articles.xml.bz2"</span>
Line 575 ⟶ 631:
<span style="color: #7060A8;">curl_easy_cleanup</span><span style="color: #0000FF;">(</span><span style="color: #000000;">curl</span><span style="color: #0000FF;">)</span>
<span style="color: #7060A8;">printf</span><span style="color: #0000FF;">(</span><span style="color: #000000;">1</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"Total downloaded: %s\n"</span><span style="color: #0000FF;">,{</span><span style="color: #000000;">file_size_k</span><span style="color: #0000FF;">(</span><span style="color: #000000;">tbr</span><span style="color: #0000FF;">)})</span>
<!--</
{{out}}
<pre>
Line 588 ⟶ 644:
=={{header|Raku}}==
I misunderstood the data format and now just copy verbatim from Julia entry the processing logics ..
<syntaxhighlight lang="raku"
use LWP::Simple;
Line 654 ⟶ 710:
my $ua = CustomLWP.new: URL => $URL ;
$ua.CustomRequest>>.say</
{{out}}
<pre>
Line 662 ⟶ 718:
pond
livre
</pre>
=={{header|Wren}}==
{{trans|Julia}}
{{libheader|libcurl}}
{{libheader|libbzip2}}
{{libheader|Wren-pattern}}
An embedded program so we can use libcurl and libbzip2.
Rather than downloading the full 800MB .bz2 file and then decompressing it, we abort the download after receiving no more than the first 512 KB and then decompress that ignoring the resultant BZ_UNEXPECTED_EOF error. This turns out to be enough to find the first 22 French words.
<syntaxhighlight lang="wren">/* WiktionaryDumps_to_words.wren */
import "./pattern" for Pattern
var CURLOPT_URL = 10002
var CURLOPT_FOLLOWLOCATION = 52
var CURLOPT_WRITEFUNCTION = 20011
var CURLOPT_WRITEDATA = 10001
foreign class Buffer {
construct new() {} // C will allocate buffer of a suitable size
foreign value // returns buffer contents as a string after decompression
}
foreign class Curl {
construct easyInit() {}
foreign easySetOpt(opt, param)
foreign easyPerform()
foreign easyCleanup()
}
var curl = Curl.easyInit()
var getContent = Fn.new { |url|
var buffer = Buffer.new()
curl.easySetOpt(CURLOPT_URL, url)
curl.easySetOpt(CURLOPT_FOLLOWLOCATION, 1)
curl.easySetOpt(CURLOPT_WRITEFUNCTION, 0) // write function to be supplied by C
curl.easySetOpt(CURLOPT_WRITEDATA, buffer)
curl.easyPerform()
return buffer.value
}
var url = "https://dumps.wikimedia.org/enwiktionary/latest/enwiktionary-latest-pages-articles.xml.bz2"
var content = getContent.call(url)
curl.easyCleanup()
var lines = content.split("\n")
var title = "<title>"
var txtOpen = "<text"
var txtClose = "</text>"
var langMark = "==French=="
var gotTextLast = false
var titleWord = ""
var p = Pattern.new("<title>[+1^<]<//title>")
for (line in lines) {
if (line.indexOf(title) >= 0) {
gotTextLast = false
var m = p.find(line)
titleWord = m ? m.capsText[0] : ""
} else if (line.indexOf(txtOpen) >= 0) {
gotTextLast = true
} else if (line.indexOf(langMark) >= 0) {
if (gotTextLast && titleWord != "") System.print(titleWord)
gotTextLast = false
} else if (line.indexOf(txtClose) >= 0) {
gotTextLast = false
}
}</syntaxhighlight>
<br>
We now embed this script in the following C program, build and run.
<syntaxhighlight lang="c">/* gcc WiktionaryDumps_to_words.c -o WiktionaryDumps_to_words -lcurl -lbz2 -lwren -lm */
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <curl/curl.h>
#include <bzlib.h>
#include "wren.h"
struct MemoryStruct {
char *memory;
size_t size;
};
const size_t LIMIT = 512 * 1024;
/* C <=> Wren interface functions */
static size_t WriteMemoryCallback(void *contents, size_t size, size_t nmemb, void *userp) {
size_t realsize = size * nmemb;
struct MemoryStruct *mem = (struct MemoryStruct *)userp;
size_t size_needed = mem->size + realsize + 1;
if (size_needed > LIMIT) return -1; // abort download
char *ptr = realloc(mem->memory, size_needed);
if(!ptr) {
/* out of memory! */
printf("not enough memory (realloc returned NULL)\n");
return 0;
}
mem->memory = ptr;
memcpy(&(mem->memory[mem->size]), contents, realsize);
mem->size += realsize;
mem->memory[mem->size] = 0;
return realsize;
}
void C_bufferAllocate(WrenVM* vm) {
struct MemoryStruct *ms = (struct MemoryStruct *)wrenSetSlotNewForeign(vm, 0, 0, sizeof(struct MemoryStruct));
ms->memory = malloc(1);
ms->size = 0;
}
void C_bufferFinalize(void* data) {
struct MemoryStruct *ms = (struct MemoryStruct *)data;
free(ms->memory);
}
void C_curlAllocate(WrenVM* vm) {
CURL** pcurl = (CURL**)wrenSetSlotNewForeign(vm, 0, 0, sizeof(CURL*));
*pcurl = curl_easy_init();
}
void C_value(WrenVM* vm) {
struct MemoryStruct *ms = (struct MemoryStruct *)wrenGetSlotForeign(vm, 0);
/* decompress string before returning to Wren */
unsigned int destLen = ms->size * 5; // should be more than enough
char *dest = malloc(destLen);
int ret = BZ2_bzBuffToBuffDecompress(dest, &destLen, ms->memory, ms->size, 0, 0);
/* should get a 'compressed data ends unexpectedly' error here which we ignore
but report any other error */
if (ret != BZ_UNEXPECTED_EOF && ret != BZ_OK) printf("error number %d occurred", ret);
char *ptr = realloc(ms->memory, destLen);
if(!ptr) {
/* out of memory! */
printf("not enough memory (realloc returned NULL)\n");
return;
}
ms->memory = ptr;
memcpy(ms->memory, dest, destLen);
ms->size = destLen;
wrenSetSlotString(vm, 0, ms->memory);
free(dest);
}
void C_easyPerform(WrenVM* vm) {
CURL* curl = *(CURL**)wrenGetSlotForeign(vm, 0);
curl_easy_perform(curl);
}
void C_easyCleanup(WrenVM* vm) {
CURL* curl = *(CURL**)wrenGetSlotForeign(vm, 0);
curl_easy_cleanup(curl);
}
void C_easySetOpt(WrenVM* vm) {
CURL* curl = *(CURL**)wrenGetSlotForeign(vm, 0);
CURLoption opt = (CURLoption)wrenGetSlotDouble(vm, 1);
if (opt < 10000) {
long lparam = (long)wrenGetSlotDouble(vm, 2);
curl_easy_setopt(curl, opt, lparam);
} else if (opt < 20000) {
if (opt == CURLOPT_WRITEDATA) {
struct MemoryStruct *ms = (struct MemoryStruct *)wrenGetSlotForeign(vm, 2);
curl_easy_setopt(curl, opt, (void *)ms);
} else if (opt == CURLOPT_URL) {
const char *url = wrenGetSlotString(vm, 2);
curl_easy_setopt(curl, opt, url);
}
} else if (opt < 30000) {
if (opt == CURLOPT_WRITEFUNCTION) {
curl_easy_setopt(curl, opt, &WriteMemoryCallback);
}
}
}
WrenForeignClassMethods bindForeignClass(WrenVM* vm, const char* module, const char* className) {
WrenForeignClassMethods methods;
methods.allocate = NULL;
methods.finalize = NULL;
if (strcmp(module, "main") == 0) {
if (strcmp(className, "Buffer") == 0) {
methods.allocate = C_bufferAllocate;
methods.finalize = C_bufferFinalize;
} else if (strcmp(className, "Curl") == 0) {
methods.allocate = C_curlAllocate;
}
}
return methods;
}
WrenForeignMethodFn bindForeignMethod(
WrenVM* vm,
const char* module,
const char* className,
bool isStatic,
const char* signature) {
if (strcmp(module, "main") == 0) {
if (strcmp(className, "Buffer") == 0) {
if (!isStatic && strcmp(signature, "value") == 0) return C_value;
} else if (strcmp(className, "Curl") == 0) {
if (!isStatic && strcmp(signature, "easySetOpt(_,_)") == 0) return C_easySetOpt;
if (!isStatic && strcmp(signature, "easyPerform()") == 0) return C_easyPerform;
if (!isStatic && strcmp(signature, "easyCleanup()") == 0) return C_easyCleanup;
}
}
return NULL;
}
static void writeFn(WrenVM* vm, const char* text) {
printf("%s", text);
}
void errorFn(WrenVM* vm, WrenErrorType errorType, const char* module, const int line, const char* msg) {
switch (errorType) {
case WREN_ERROR_COMPILE:
printf("[%s line %d] [Error] %s\n", module, line, msg);
break;
case WREN_ERROR_STACK_TRACE:
printf("[%s line %d] in %s\n", module, line, msg);
break;
case WREN_ERROR_RUNTIME:
printf("[Runtime Error] %s\n", msg);
break;
}
}
char *readFile(const char *fileName) {
FILE *f = fopen(fileName, "r");
fseek(f, 0, SEEK_END);
long fsize = ftell(f);
rewind(f);
char *script = malloc(fsize + 1);
fread(script, 1, fsize, f);
fclose(f);
script[fsize] = 0;
return script;
}
static void loadModuleComplete(WrenVM* vm, const char* module, WrenLoadModuleResult result) {
if( result.source) free((void*)result.source);
}
WrenLoadModuleResult loadModule(WrenVM* vm, const char* name) {
WrenLoadModuleResult result = {0};
if (strcmp(name, "random") != 0 && strcmp(name, "meta") != 0) {
result.onComplete = loadModuleComplete;
char fullName[strlen(name) + 6];
strcpy(fullName, name);
strcat(fullName, ".wren");
result.source = readFile(fullName);
}
return result;
}
int main(int argc, char **argv) {
WrenConfiguration config;
wrenInitConfiguration(&config);
config.writeFn = &writeFn;
config.errorFn = &errorFn;
config.bindForeignClassFn = &bindForeignClass;
config.bindForeignMethodFn = &bindForeignMethod;
config.loadModuleFn = &loadModule;
WrenVM* vm = wrenNewVM(&config);
const char* module = "main";
const char* fileName = "WiktionaryDumps_to_words.wren";
char *script = readFile(fileName);
WrenInterpretResult result = wrenInterpret(vm, module, script);
switch (result) {
case WREN_RESULT_COMPILE_ERROR:
printf("Compile Error!\n");
break;
case WREN_RESULT_RUNTIME_ERROR:
printf("Runtime Error!\n");
break;
case WREN_RESULT_SUCCESS:
break;
}
wrenFreeVM(vm);
free(script);
return 0;
}</syntaxhighlight>
{{out}}
<pre>
gratis
gratuit
livre
chien
pond
pies
pie
A
connotation
minute
trade
adjective
adjectival
substantive
patronage
deal
merchandise
eagle
f
fa
fable
a-
</pre>
| |||