Skip to content

fix: resolve TESSDATA_PREFIX path correctly for all Tesseract versions #2257

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
DhanushVarma-2 wants to merge 1 commit into
base: master
Choose a base branch
from
+29 −3
Open

fix: resolve TESSDATA_PREFIX path correctly for all Tesseract versions #2257

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 29 additions & 3 deletions src/lib_ccx/ocr.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -261,20 +261,46 @@ void *init_ocr(int lang_index)
}

ctx->api = TessBaseAPICreate();

/* Build the correct tessdata path for TessBaseAPIInit4.
* probe_tessdata_location() returns a base dir e.g. "/opt/homebrew/share/".
* TessBaseAPIInit4 expects "<base>/tessdata" as the data path.
* If TESSDATA_PREFIX already points at the tessdata dir itself,
* avoid appending "tessdata" a second time. */
char tess_path[1024];
size_t tp_len = strlen(tessdata_path);
int already_has_tessdata = (tp_len >= 8 &&
(strcmp(tessdata_path + tp_len - 8, "tessdata/") == 0 ||
strcmp(tessdata_path + tp_len - 8, "tessdata") == 0));
if (already_has_tessdata)
{
snprintf(tess_path, sizeof(tess_path), "%s", tessdata_path);
}
else
{
snprintf(tess_path, sizeof(tess_path), "%s%stessdata",
tessdata_path,
(tessdata_path[tp_len - 1] == '/' || tessdata_path[tp_len - 1] == '\\') ? "" : "/");
}

mprint("CCExtractor: using tessdata path: %s\n", tess_path);

if (!strncmp("4.", TessVersion(), 2) || !strncmp("5.", TessVersion(), 2))
{
char tess_path[1024];
snprintf(tess_path, 1024, "%s%s%s", tessdata_path, "/", "tessdata");
if (ccx_options.ocr_oem < 0)
{
ccx_options.ocr_oem = 1;
}
ret = TessBaseAPIInit4(ctx->api, tess_path, lang, ccx_options.ocr_oem, NULL, 0, &pars_vec,
&pars_values, 1, false);
}
else
{
if (ccx_options.ocr_oem < 0)
{
ccx_options.ocr_oem = 0;
ret = TessBaseAPIInit4(ctx->api, tessdata_path, lang, ccx_options.ocr_oem, NULL, 0, &pars_vec,
}
ret = TessBaseAPIInit4(ctx->api, tess_path, lang, ccx_options.ocr_oem, NULL, 0, &pars_vec,
&pars_values, 1, false);
}

Expand Down
Loading