docling-ibm-models 2.0.6__tar.gz → 2.0.8__tar.gz

{docling_ibm_models-2.0.6 → docling_ibm_models-2.0.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling-ibm-models
-Version: 2.0.6
+Version: 2.0.8
 Summary: This package contains the AI models used by the Docling PDF conversion package
 License: MIT
 Keywords: docling,convert,document,pdf,layout model,segmentation,table structure,table former
@@ -18,12 +18,12 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Dist: Pillow (>=10.0.0,<11.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)
 Requires-Dist: jsonlines (>=3.1.0,<4.0.0)
-Requires-Dist: numpy (>=1.24.4,<2.0.0) ; python_version < "3.13"
-Requires-Dist: numpy (>=2.1.0,<3.0.0) ; python_version >= "3.13"
+Requires-Dist: numpy (>=1.24.4,<3.0.0)
 Requires-Dist: opencv-python-headless (>=4.6.0.66,<5.0.0.0)
 Requires-Dist: torch (>=2.2.2,<3.0.0)
 Requires-Dist: torchvision (>=0,<1)

{docling_ibm_models-2.0.6 → docling_ibm_models-2.0.8}/docling_ibm_models/tableformer/data_management/matching_post_processor.py

@@ -96,10 +96,10 @@ class MatchingPostProcessor:
                         if cell["cell_class"] <= 1:
                             allow_class = False
                     else:
-                        print("***")
-                        print("no cell_class in...")
-                        print(cell)
-                        print("***")
+                        self._log().debug("***")
+                        self._log().debug("no cell_class in...")
+                        self._log().debug(cell)
+                        self._log().debug("***")
                     if allow_class:
                         match_list = matches[pdf_cell_id]
                         for match in match_list:

{docling_ibm_models-2.0.6 → docling_ibm_models-2.0.8}/docling_ibm_models/tableformer/data_management/tf_cell_matcher.py

@@ -264,7 +264,7 @@ class CellMatcher:
         r, o = otsl.html_to_otsl(table_html_structure, None, False, False, True, False)
         if not r:
             ermsg = "ERR#: COULD NOT CONVERT TO RS THIS TABLE TO COMPUTE SPANS"
-            print(ermsg)
+            self._log().debug(ermsg)
         else:
             otsl_spans = o["otsl_spans"]
 

{docling_ibm_models-2.0.6 → docling_ibm_models-2.0.8}/docling_ibm_models/tableformer/data_management/tf_predictor.py

@@ -30,6 +30,8 @@ from docling_ibm_models.tableformer.utils.app_profiler import AggProfiler
 # LOG_LEVEL = logging.DEBUG
 LOG_LEVEL = logging.WARN
 
+logger = s.get_custom_logger(__name__, LOG_LEVEL)
+
 
 class bcolors:
     HEADER = "\033[95m"
@@ -53,17 +55,17 @@ def otsl_sqr_chk(rs_list, logdebug):
 
         totcelnum = rs_list.count("fcel") + rs_list.count("ecel")
         if logdebug:
-            print("Total number of cells = {}".format(totcelnum))
+            logger.debug("Total number of cells = {}".format(totcelnum))
 
         for ind, ln in enumerate(rs_list_split):
             ln.append("nl")
             if logdebug:
-                print("{}".format(ln))
+                logger.debug("{}".format(ln))
             if len(ln) != init_tag_len:
                 isSquare = False
         if isSquare:
             if logdebug:
-                print(
+                logger.debug(
                     "{}*OK* Table is square! *OK*{}".format(
                         bcolors.OKGREEN, bcolors.ENDC
                     )
@@ -71,8 +73,8 @@ def otsl_sqr_chk(rs_list, logdebug):
         else:
             if logdebug:
                 err_name = "{}***** ERR ******{}"
-                print(err_name.format(bcolors.FAIL, bcolors.ENDC))
-                print(
+                logger.debug(err_name.format(bcolors.FAIL, bcolors.ENDC))
+                logger.debug(
                     "{}*ERR* Table is not square! *ERR*{}".format(
                         bcolors.FAIL, bcolors.ENDC
                     )

{docling_ibm_models-2.0.6 → docling_ibm_models-2.0.8}/docling_ibm_models/tableformer/otsl.py

@@ -49,15 +49,15 @@ def otsl_sqr_chk(rs_list, name, logdebug):
                 isSquare = False
         if isSquare:
             if logdebug:
-                print(
+                logger.debug(
                     "{}*OK* Table is square! *OK*{}".format(
                         bcolors.OKGREEN, bcolors.ENDC
                     )
                 )
         else:
             err_name = "{}*ERR* " + name + " *ERR*{}"
-            print(err_name.format(bcolors.FAIL, bcolors.ENDC))
-            print(
+            logger.debug(err_name.format(bcolors.FAIL, bcolors.ENDC))
+            logger.debug(
                 "{}*ERR* Table is not square! *ERR*{}".format(
                     bcolors.FAIL, bcolors.ENDC
                 )
@@ -89,9 +89,9 @@ def otsl_tags_cells_sync_chk(rs_list, cells, name, logdebug):
             countCellTags += 1
     if countCellTags != len(cells):
         err_name = "{}*!ERR* " + name + " *ERR!*{}"
-        print(err_name.format(bcolors.FAIL, bcolors.ENDC))
+        logger.debug(err_name.format(bcolors.FAIL, bcolors.ENDC))
         err_msg = "{}*!ERR* Tags are not in sync with cells! *ERR!*{}"
-        print(err_msg.format(bcolors.FAIL, bcolors.ENDC))
+        logger.debug(err_msg.format(bcolors.FAIL, bcolors.ENDC))
         isGood = False
     return isGood
 
@@ -131,11 +131,13 @@ def otsl_to_html(rs_list, logdebug):
         return rs_list
     html_table = []
     if logdebug:
-        print("{}*Reconstructing HTML...*{}".format(bcolors.WARNING, bcolors.ENDC))
+        logger.debug(
+            "{}*Reconstructing HTML...*{}".format(bcolors.WARNING, bcolors.ENDC)
+        )
 
     if not otsl_sqr_chk(rs_list, "---", logdebug):
         # PAD TABLE TO SQUARE
-        print("{}*Padding to square...*{}".format(bcolors.WARNING, bcolors.ENDC))
+        logger.debug("{}*Padding to square...*{}".format(bcolors.WARNING, bcolors.ENDC))
         rs_list = otsl_pad_to_sqr(rs_list, "lcel")
 
     # 2D structure, line by line:
@@ -144,7 +146,7 @@ def otsl_to_html(rs_list, logdebug):
     ]
 
     if logdebug:
-        print("")
+        logger.debug("")
 
     # Sequentially store indexes of 2D spans that were registered to avoid re-registering them
     registry_2d_span = []
@@ -182,9 +184,9 @@ def otsl_to_html(rs_list, logdebug):
                         span = True
                 # Check if it has vertical span:
                 if rs_row_ind + 1 < len(rs_list_split):
-                    # print(">>>")
-                    # print(rs_list_split[rs_row_ind + 1])
-                    # print(">>> rs_cell_ind = {}".format(rs_cell_ind))
+                    # logger.debug(">>>")
+                    # logger.debug(rs_list_split[rs_row_ind + 1])
+                    # logger.debug(">>> rs_cell_ind = {}".format(rs_cell_ind))
                     if rs_list_split[rs_row_ind + 1][rs_cell_ind] == "ucel":
                         ddist = otsl_check_down(rs_list_split, rs_cell_ind, rs_row_ind)
                         span = True
@@ -198,12 +200,12 @@ def otsl_to_html(rs_list, logdebug):
                         span = True
                         # Check if this 2D span was already registered,
                         # If not - register, if yes - cancel span
-                        # print("rs_cell_ind: {}, xrdist:{}".format(rs_cell_ind, xrdist))
-                        # print("rs_row_ind: {}, xddist:{}".format(rs_cell_ind, xrdist))
+                        # logger.debug("rs_cell_ind: {}, xrdist:{}".format(rs_cell_ind, xrdist))
+                        # logger.debug("rs_row_ind: {}, xddist:{}".format(rs_cell_ind, xrdist))
                         for x in range(rs_cell_ind, xrdist + rs_cell_ind):
                             for y in range(rs_row_ind, xddist + rs_row_ind):
                                 reg2dind = str(x) + "_" + str(y)
-                                # print(reg2dind)
+                                # logger.debug(reg2dind)
                                 if reg2dind in registry_2d_span:
                                     # Cell of the span is already in, cancel current span
                                     span = False
@@ -232,9 +234,13 @@ def otsl_to_html(rs_list, logdebug):
         html_table.extend(html_list)
 
     if logdebug:
-        print("*********************** registry_2d_span ***************************")
-        print(registry_2d_span)
-        print("********************************************************************")
+        logger.debug(
+            "*********************** registry_2d_span ***************************"
+        )
+        logger.debug(registry_2d_span)
+        logger.debug(
+            "********************************************************************"
+        )
 
     return html_table
 
@@ -316,20 +322,24 @@ def html_to_otsl(table, writer, logdebug, extra_debug, include_html, use_writer)
     current_line_expands = []
 
     if logdebug:
-        print("")
-        print("*** {}: {} ***".format(table["split"], table["filename"]))
+        logger.debug("")
+        logger.debug("*** {}: {} ***".format(table["split"], table["filename"]))
 
     colnum = 0
 
     if extra_debug:
-        print("========================== Input HTML ============================")
-        print(table_html_structure["tokens"])
-        print("==================================================================")
+        logger.debug(
+            "========================== Input HTML ============================"
+        )
+        logger.debug(table_html_structure["tokens"])
+        logger.debug(
+            "=================================================================="
+        )
 
     if logdebug:
-        print("********")
-        print("* OTSL *")
-        print("********")
+        logger.debug("********")
+        logger.debug("* OTSL *")
+        logger.debug("********")
 
     for i in range(len(table_html_structure["tokens"])):
         html_tag = table_html_structure["tokens"][i]
@@ -377,7 +387,7 @@ def html_to_otsl(table, writer, logdebug, extra_debug, include_html, use_writer)
                         extra_columns = pre_line_len - cur_line_len - 1
                         if extra_columns > 0:
                             if extra_debug:
-                                print(
+                                logger.debug(
                                     "Extra columns needed in row: {}".format(
                                         extra_columns
                                     )
@@ -534,11 +544,11 @@ def html_to_otsl(table, writer, logdebug, extra_debug, include_html, use_writer)
                 writer.write(out_line)
 
     if logdebug:
-        print("{}Reconstructed HTML:{}".format(bcolors.OKGREEN, bcolors.ENDC))
-        print(rHTML)
+        logger.debug("{}Reconstructed HTML:{}".format(bcolors.OKGREEN, bcolors.ENDC))
+        logger.debug(rHTML)
         # original HTML
         oHTML = out_line["html"]["html_structure"]
-        print("{}Original HTML:{}".format(bcolors.OKBLUE, bcolors.ENDC))
-        print(oHTML)
+        logger.debug("{}Original HTML:{}".format(bcolors.OKBLUE, bcolors.ENDC))
+        logger.debug(oHTML)
 
     return True, out_line

{docling_ibm_models-2.0.6 → docling_ibm_models-2.0.8}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling-ibm-models"
-version = "2.0.6"  # DO NOT EDIT, updated automatically
+version = "2.0.8"  # DO NOT EDIT, updated automatically
 description = "This package contains the AI models used by the Docling PDF conversion package"
 authors = ["Nikos Livathinos <nli@zurich.ibm.com>", "Maxim Lysak <mly@zurich.ibm.com>", "Ahmed Nassar <ahn@zurich.ibm.com>", "Christoph Auer <cau@zurich.ibm.com>", "Michele Dolfi <dol@zurich.ibm.com>", "Peter Staar <taa@zurich.ibm.com>"]
 license = "MIT"
@@ -24,10 +24,7 @@ packages = [
 python = "^3.9"
 torch = "^2.2.2"
 torchvision = "^0"
-numpy = [
-    { version = "^2.1.0", markers = 'python_version >= "3.13"' },
-    { version = "^1.24.4", markers = 'python_version < "3.13"' },
-]
+numpy = ">=1.24.4,<3.0.0"
 jsonlines = "^3.1.0"
 Pillow = "^10.0.0"
 tqdm = "^4.64.0"
@@ -63,6 +60,15 @@ torchvision = [
   {markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~0.17.2"}
 ]
 
+[tool.poetry.group.constraints]
+optional = true
+
+[tool.poetry.group.constraints.dependencies]
+numpy = [
+    { version = ">=1.24.4,<3.0.0", markers = 'python_version >= "3.10"' },
+    { version = ">=1.24.4,<2.1.0", markers = 'python_version < "3.10"' },
+]
+
 
 [build-system]
 requires = ["poetry-core>=1.0.0"]