feat(flatfile): warn on missing or mismatched log format-version

This commit is contained in:
2026-05-04 17:17:33 +03:00
parent a9b181beb7
commit 48b89460b7
3 changed files with 65 additions and 2 deletions

View File

@@ -205,6 +205,15 @@ _ff_state_build(ff_contact_state_t* state)
state->bom_len = ff_skip_bom(fp);
int file_version = ff_read_format_version(fp);
if (file_version == 0) {
log_warning("flatfile: %s has no format-version marker, expected %d",
state->filepath, FLATFILE_FORMAT_VERSION);
} else if (file_version != FLATFILE_FORMAT_VERSION) {
log_warning("flatfile: %s format-version %d does not match expected %d",
state->filepath, file_version, FLATFILE_FORMAT_VERSION);
}
state->n_entries = 0;
state->total_lines = 0;

View File

@@ -24,8 +24,13 @@
// --- Constants ---
#define DIR_FLATLOG "flatlog"
#define FLATFILE_HEADER "# profanity chat log — UTF-8, LF line endings\n# vim: set fileencoding=utf-8 fileformat=unix :\n"
#define DIR_FLATLOG "flatlog"
#define FLATFILE_FORMAT_VERSION 1
#define FF_VERSION_PREFIX "# format-version: "
#define FLATFILE_HEADER \
"# profanity chat log — UTF-8, LF line endings\n" \
"# format-version: 1\n" \
"# vim: set fileencoding=utf-8 fileformat=unix :\n"
#define FF_MAX_LINE_LEN (10 * 1024 * 1024) /* 10 MB — reject lines longer than this */
#define FF_MAX_LMC_DEPTH 100 /* max correction chain depth */
@@ -125,6 +130,11 @@ char* ff_unescape_meta_value(const char* val);
// Skip UTF-8 BOM if present; returns 3 if skipped, 0 otherwise.
int ff_skip_bom(FILE* fp);
// Scan leading '#' comment lines for the format-version marker. Returns
// the version found, 0 if no marker is present, or -1 on read error.
// File position is rewound to the start of the comment block on entry.
int ff_read_format_version(FILE* fp);
char* ff_readline(FILE* fp, gboolean* truncated);
void ff_write_line(FILE* fp, const char* timestamp, const char* type, const char* enc,
const char* stanza_id, const char* archive_id, const char* replace_id,

View File

@@ -16,6 +16,7 @@
#include <sys/stat.h>
#include <glib.h>
#include <glib/gstdio.h>
#include <limits.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
@@ -338,6 +339,49 @@ ff_skip_bom(FILE* fp)
return 0;
}
// Format-version helper
// =========================================================================
//
// Scan leading '#' comment lines for `# format-version: <N>`. Stops at
// the first non-comment line or after FF_VERSION_SCAN_MAX comments.
// Restores fp to its position at entry, so callers can re-parse the
// header normally afterwards.
#define FF_VERSION_SCAN_MAX 16
int
ff_read_format_version(FILE* fp)
{
long start = ftell(fp);
if (start < 0)
return -1;
int version = 0;
size_t prefix_len = strlen(FF_VERSION_PREFIX);
for (int i = 0; i < FF_VERSION_SCAN_MAX; i++) {
gboolean truncated = FALSE;
char* line = ff_readline(fp, &truncated);
if (!line)
break;
if (line[0] != '#') {
free(line);
break;
}
if (strncmp(line, FF_VERSION_PREFIX, prefix_len) == 0) {
char* endptr = NULL;
long v = strtol(line + prefix_len, &endptr, 10);
if (endptr != line + prefix_len && v > 0 && v <= INT_MAX)
version = (int)v;
free(line);
break;
}
free(line);
}
fseek(fp, start, SEEK_SET);
return version;
}
// Readline helper
// =========================================================================
//