From 53fd5fb2a5da9a4c42bd1964a3ed1d2427f8637e Mon Sep 17 00:00:00 2001 From: vahidrezanezhad Date: Wed, 14 Aug 2024 14:42:37 +0200 Subject: [PATCH] resolving #106 for pyproject.toml test --- qurator/eynollah/cli.py | 6 +++++- qurator/eynollah/eynollah.py | 9 ++++++--- 2 files changed, 11 insertions(+), 4 deletions(-) diff --git a/qurator/eynollah/cli.py b/qurator/eynollah/cli.py index 6c6561f..b0f55cd 100644 --- a/qurator/eynollah/cli.py +++ b/qurator/eynollah/cli.py @@ -236,7 +236,11 @@ def layout(image, out, dir_in, model, save_images, save_layout, save_deskewed, s reading_order_machine_based=reading_order_machine_based, do_ocr=do_ocr, ) - eynollah.run() + if dir_in: + eynollah.run() + else: + pcgts = eynollah.run() + eynollah.writer.write_pagexml(pcgts) if __name__ == "__main__": main() diff --git a/qurator/eynollah/eynollah.py b/qurator/eynollah/eynollah.py index 3f078b0..b27d269 100644 --- a/qurator/eynollah/eynollah.py +++ b/qurator/eynollah/eynollah.py @@ -3797,7 +3797,8 @@ class Eynollah: pcgts = self.writer.build_pagexml_full_layout(contours_only_text_parent, contours_only_text_parent_h, page_coord, order_text_new, id_of_texts_tot, all_found_textline_polygons, all_found_textline_polygons_h, all_box_coord, all_box_coord_h, polygons_of_images, contours_tables, polygons_of_drop_capitals, polygons_of_marginals, all_found_textline_polygons_marginals, all_box_coord_marginals, slopes, slopes_h, slopes_marginals, cont_page, polygons_lines_xml, ocr_all_textlines) self.logger.info("Job done in %.1fs", time.time() - t0) - ##return pcgts + if not self.dir_in: + return pcgts else: @@ -3872,9 +3873,11 @@ class Eynollah: self.logger.info("detection of reading order took %.1fs", time.time() - t_order) pcgts = self.writer.build_pagexml_no_full_layout(txt_con_org, page_coord, order_text_new, id_of_texts_tot, all_found_textline_polygons, all_box_coord, polygons_of_images, polygons_of_marginals, all_found_textline_polygons_marginals, all_box_coord_marginals, slopes, slopes_marginals, cont_page, polygons_lines_xml, contours_tables, ocr_all_textlines) self.logger.info("Job done in %.1fs", time.time() - t0) - ##return pcgts + if not self.dir_in: + return pcgts #print("text region early 7 in %.1fs", time.time() - t0) - self.writer.write_pagexml(pcgts) + if self.dir_in: + self.writer.write_pagexml(pcgts) #self.logger.info("Job done in %.1fs", time.time() - t0) #print("Job done in %.1fs", time.time() - t0)