From 6c364dc99766bfd3bd86cd262db37b1a766dca1e Mon Sep 17 00:00:00 2001 From: Přemysl Eric Janouch Date: Wed, 6 Oct 2021 20:13:43 +0200 Subject: Add an implementation of tabfile The original one is a horrible thing. Now we're self-reliant. --- CMakeLists.txt | 2 +- src/tabfile.c | 163 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ src/transform.c | 2 +- 3 files changed, 165 insertions(+), 2 deletions(-) create mode 100644 src/tabfile.c diff --git a/CMakeLists.txt b/CMakeLists.txt index e1cff26..bd42553 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -163,7 +163,7 @@ if (gtk_FOUND) endif () # Tools -set (tools add-pronunciation query-tool transform) +set (tools tabfile add-pronunciation query-tool transform) foreach (tool ${tools}) add_executable (${tool} EXCLUDE_FROM_ALL src/${tool}.c ${project_common_sources}) diff --git a/src/tabfile.c b/src/tabfile.c new file mode 100644 index 0000000..0bcbff3 --- /dev/null +++ b/src/tabfile.c @@ -0,0 +1,163 @@ +/* + * A clean reimplementation of StarDict's tabfile + * + * Copyright (c) 2020 - 2021, Přemysl Eric Janouch + * + * Permission to use, copy, modify, and/or distribute this software for any + * purpose with or without fee is hereby granted. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY + * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION + * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN + * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + * + */ + +#include +#include +#include +#include +#include + +#include +#include + +#include "stardict.h" +#include "stardict-private.h" +#include "generator.h" +#include "utils.h" + +static gboolean +set_data_error (GError **error, const char *message) +{ + g_set_error_literal (error, G_IO_ERROR, G_IO_ERROR_INVALID_DATA, message); + return FALSE; +} + +static const gchar escapes[256] = { ['n'] = '\n', ['t'] = '\t', ['\\'] = '\\' }; + +static gboolean +inplace_unescape (char *line, GError **error) +{ + gboolean escape = FALSE; + char *dest = line; + for (char *src = line; *src; src++) + { + if (escape) + { + escape = FALSE; + if (!(*dest++ = escapes[(guchar) *src])) + return set_data_error (error, "unsupported escape"); + } + else if (*src == '\\') + escape = TRUE; + else + *dest++ = *src; + } + if (escape) + return set_data_error (error, "trailing escape character"); + + *dest = 0; + return TRUE; +} + +static gboolean +import_line (Generator *generator, char *line, size_t len, GError **error) +{ + if (!len) + return TRUE; + + char *separator = strchr (line, '\t'); + if (!separator) + return set_data_error (error, "keyword separator not found"); + + *separator++ = 0; + if (strchr (line, '\\')) + // The index wouldn't be sorted correctly with our method + return set_data_error (error, "escapes not allowed in keywords"); + + char *newline = strpbrk (separator, "\r\n"); + if (newline) + *newline = 0; + + if (!inplace_unescape (line, error) + || !inplace_unescape (separator, error)) + return FALSE; + + generator_begin_entry (generator); + return generator_write_string (generator, separator, TRUE, error) + && generator_finish_entry (generator, line, error); +} + +static gboolean +transform (FILE *fsorted, Generator *generator, GError **error) +{ + char *line = NULL; + size_t size = 0, ln = 1; + for (ssize_t read; (read = getline (&line, &size, fsorted)) >= 0; ln++) + if (!import_line (generator, line, read, error)) + break; + + free (line); + if (ferror (fsorted)) + { + g_set_error_literal (error, G_IO_ERROR, + g_io_error_from_errno (errno), g_strerror (errno)); + return FALSE; + } + if (!feof (fsorted)) + { + // You'll only get good line number output with presorted input! + g_prefix_error (error, "line %zu: ", ln); + return FALSE; + } + return TRUE; +} + +int +main (int argc, char *argv[]) +{ + // The GLib help includes an ellipsis character, for some reason + (void) setlocale (LC_ALL, ""); + + GError *error = NULL; + GOptionContext *ctx = g_option_context_new ("output-basename < input"); + g_option_context_set_summary (ctx, + "Create a StarDict dictionary from plaintext."); + if (!g_option_context_parse (ctx, &argc, &argv, &error)) + fatal ("Error: option parsing failed: %s\n", error->message); + + if (argc != 2) + fatal ("%s", g_option_context_get_help (ctx, TRUE, FALSE)); + g_option_context_free (ctx); + + // This actually implements stardict_strcmp(), POSIX-compatibly. + // Your sort(1) is not expected to be stable by default, like bsdsort is. + FILE *fsorted = popen ("LC_ALL=C sort -t'\t' -k1f,1", "r"); + if (!fsorted) + fatal ("%s: %s\n", "popen", g_strerror (errno)); + + Generator *generator = generator_new (argv[1], &error); + if (!generator) + fatal ("Error: failed to create the output dictionary: %s\n", + error->message); + + StardictInfo *info = generator->info; + info->version = SD_VERSION_3_0_0; + info->book_name = g_strdup (argv[1]); + info->same_type_sequence = g_strdup ("m"); + + // This gets incremented each time an entry is finished + info->word_count = 0; + + if (!transform (fsorted, generator, &error) + || !generator_finish (generator, &error)) + fatal ("Error: failed to write the dictionary: %s\n", error->message); + + generator_free (generator); + fclose (fsorted); + return 0; +} diff --git a/src/transform.c b/src/transform.c index e3e8d4d..2144c6b 100644 --- a/src/transform.c +++ b/src/transform.c @@ -3,7 +3,7 @@ * * The external filter needs to process NUL-separated textual entries. * - * Example: transform input.info output -- perl -p0e s/bullshit/soykaf/g + * Example: transform input.ifo output -- perl -p0e s/bullshit/soykaf/g * * Copyright (c) 2020, Přemysl Eric Janouch * -- cgit v1.2.3-70-g09d2