docling-parse 2.0.2__tar.gz → 2.0.4__tar.gz

{docling_parse-2.0.2 → docling_parse-2.0.4}/CHANGELOG.md

@@ -1,3 +1,15 @@
+## [v2.0.4](https://github.com/DS4SD/docling-parse/releases/tag/v2.0.4) - 2024-11-13
+
+### Fix
+
+* Removing asserts that break parse-v2 ([#55](https://github.com/DS4SD/docling-parse/issues/55)) ([`bb978c2`](https://github.com/DS4SD/docling-parse/commit/bb978c2918f3711aa838006a4b45f5701a561ef5))
+
+## [v2.0.3](https://github.com/DS4SD/docling-parse/releases/tag/v2.0.3) - 2024-11-05
+
+### Fix
+
+* Replace all the FATAL with ERROR messages in the v2 parser ([#53](https://github.com/DS4SD/docling-parse/issues/53)) ([`cd15d00`](https://github.com/DS4SD/docling-parse/commit/cd15d00ddb6c67fada0056ec068caffc003d5edc))
+
 ## [v2.0.2](https://github.com/DS4SD/docling-parse/releases/tag/v2.0.2) - 2024-10-30
 
 ### Fix

{docling_parse-2.0.2 → docling_parse-2.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling-parse
-Version: 2.0.2
+Version: 2.0.4
 Summary: Simple package to extract text with coordinates from programmatic PDFs
 Home-page: https://github.com/DS4SD/docling-parse
 License: MIT

{docling_parse-2.0.2 → docling_parse-2.0.4}/docling_parse/visualize.py

@@ -53,6 +53,13 @@ def parse_args():
         help="Enable interactive mode (default: False)",
     )
 
+    # Add an optional boolean argument for interactive mode
+    parser.add_argument(
+        "--display-text",
+        action="store_true",
+        help="Enable interactive mode (default: False)",
+    )
+
     # Add an argument for the output directory, defaulting to "./tmp"
     parser.add_argument(
         "-o",
@@ -91,11 +98,17 @@ def parse_args():
         args.interactive,
         args.output_dir,
         int(args.page),
+        args.display_text,
     )
 
 
 def visualise_v1(
-    log_level: str, pdf_path: str, interactive: str, output_dir: str, page_num: int
+    log_level: str,
+    pdf_path: str,
+    interactive: str,
+    output_dir: str,
+    page_num: int,
+    display_text: bool,
 ):
 
     parser = pdf_parser_v1()
@@ -200,7 +213,12 @@ def visualise_v1(
 
 
 def visualise_v2(
-    log_level: str, pdf_path: str, interactive: str, output_dir: str, page_num: int
+    log_level: str,
+    pdf_path: str,
+    interactive: str,
+    output_dir: str,
+    page_num: int,
+    display_text: bool,
 ):
 
     parser = pdf_parser_v2(log_level)
@@ -214,10 +232,17 @@ def visualise_v2(
 
     doc = None
 
-    if page_num == -1:
-        doc = parser.parse_pdf_from_key(doc_key)
-    else:
-        doc = parser.parse_pdf_from_key_on_page(doc_key, page_num)
+    try:
+        if page_num == -1:
+            doc = parser.parse_pdf_from_key(doc_key)
+        else:
+            doc = parser.parse_pdf_from_key_on_page(doc_key, page_num)
+    except Exception as exc:
+        print(f"Could not parse pdf-document: {exc}")
+        doc = None
+
+    if doc == None:
+        return
 
     parser.unload_document(doc_key)
 
@@ -295,6 +320,9 @@ def visualise_v2(
                         (x[3], H - y[3]),
                     ]
 
+                    if display_text:
+                        print(row[cells_header.index("text")])
+
                     if "glyph" in row[cells_header.index("text")]:
                         print(f" skip cell -> {row}")
                         continue
@@ -328,12 +356,12 @@ def visualise_v2(
 
 def main():
 
-    log_level, version, pdf, interactive, output_dir, page = parse_args()
+    log_level, version, pdf, interactive, output_dir, page, display_text = parse_args()
 
     if version == "v1":
-        visualise_v1(log_level, pdf, interactive, output_dir, page)
+        visualise_v1(log_level, pdf, interactive, output_dir, page, display_text)
     elif version == "v2":
-        visualise_v2(log_level, pdf, interactive, output_dir, page)
+        visualise_v2(log_level, pdf, interactive, output_dir, page, display_text)
     else:
         return -1
 

{docling_parse-2.0.2 → docling_parse-2.0.4}/poetry.lock

@@ -1603,13 +1603,13 @@ files = [
 
 [[package]]
 name = "tqdm"
-version = "4.66.5"
+version = "4.67.0"
 description = "Fast, Extensible Progress Meter"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "tqdm-4.66.5-py3-none-any.whl", hash = "sha256:90279a3770753eafc9194a0364852159802111925aa30eb3f9d85b0e805ac7cd"},
-    {file = "tqdm-4.66.5.tar.gz", hash = "sha256:e1020aef2e5096702d8a025ac7d16b1577279c9d63f8375b63083e9a5f0fcbad"},
+    {file = "tqdm-4.67.0-py3-none-any.whl", hash = "sha256:0cd8af9d56911acab92182e88d763100d4788bdf421d251616040cc4d44863be"},
+    {file = "tqdm-4.67.0.tar.gz", hash = "sha256:fe5a6f95e6fe0b9755e9469b77b9c3cf850048224ecaa8293d7d2d31f97d869a"},
 ]
 
 [package.dependencies]
@@ -1617,6 +1617,7 @@ colorama = {version = "*", markers = "platform_system == \"Windows\""}
 
 [package.extras]
 dev = ["pytest (>=6)", "pytest-cov", "pytest-timeout", "pytest-xdist"]
+discord = ["requests"]
 notebook = ["ipywidgets (>=6)"]
 slack = ["slack-sdk"]
 telegram = ["requests"]
@@ -1754,4 +1755,4 @@ type = ["pytest-mypy"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.9"
-content-hash = "ca4e405e008690cf2c8a893de1a1cc9a72190e61cbc0a1c7ed4ad323b06be4d5"
+content-hash = "bc52d2dc3d58424fece72dc3387eb5ab793cdc441279bcea8850a9f57caa301c"

{docling_parse-2.0.2 → docling_parse-2.0.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling-parse"
-version = "2.0.2"
+version = "2.0.4"
 description = "Simple package to extract text with coordinates from programmatic PDFs"
 authors = ["Peter Staar <taa@zurich.ibm.com>"]
 maintainers = [
@@ -69,6 +69,7 @@ pytest = "^7.4.2"
 
 [tool.poetry.group.visualisation.dependencies]
 pillow = "^10.4.0"
+tqdm = "^4.67.0"
 
 [tool.poetry.scripts]
 docling-parse = "docling_parse.run:main"

{docling_parse-2.0.2 → docling_parse-2.0.4}/src/v2/enums.h

@@ -36,7 +36,7 @@ namespace pdflib
     else if (name=="CID_FONT_TYPE_2" or name=="/CIDFontType2") { return CID_FONT_TYPE_2; }
     else
       {
-        LOG_S(FATAL) << "unknown subtype " << name;
+        LOG_S(ERROR) << "unknown subtype " << name;
         return NULL_TYPE; 
       }
   }
@@ -59,7 +59,7 @@ namespace pdflib
 
       default:
         {
-          LOG_S(FATAL) << "encountered a NULL_ENCODING";
+          LOG_S(ERROR) << "encountered a NULL_ENCODING";
           return "NULL_ENCODING";
         }
       }
@@ -90,7 +90,7 @@ namespace pdflib
     else if(name=="CMAP_RESOURCES"                          ) { return CMAP_RESOURCES; }
     else 
       {
-        LOG_S(FATAL) << __FILE__ << ":" << __LINE__ << " --> unknown encoding " << name;
+        LOG_S(ERROR) << __FILE__ << ":" << __LINE__ << " --> unknown encoding " << name;
         return NULL_ENCODING; 
       }
   }
@@ -109,7 +109,7 @@ namespace pdflib
 
       default:
         {
-          LOG_S(FATAL) << "encountered a NULL_ENCODING";
+          LOG_S(ERROR) << "encountered a NULL_ENCODING";
           return "NULL_ENCODING";
         }
       }

{docling_parse-2.0.2 → docling_parse-2.0.4}/src/v2/pdf_decoders/stream.h

@@ -253,7 +253,11 @@ namespace pdflib
   {
     if(stack.size()==0)
       {
-        LOG_S(FATAL) << "stack-size is zero!";
+	std::stringstream message;
+	message << "stack-size is zero in " << __FILE__ << ":" << __LINE__;
+
+	LOG_S(ERROR) << message.str();
+	throw std::logic_error(message.str());
       }
 
     pdf_state<GLOBAL>& state = stack.back();

{docling_parse-2.0.2 → docling_parse-2.0.4}/src/v2/pdf_resources/page_dimension.h

@@ -110,7 +110,7 @@ namespace pdflib
       }
     else
       {
-        LOG_S(FATAL) << "The page is missing the required '/MediaBox'";
+        LOG_S(ERROR) << "The page is missing the required '/MediaBox'";
       }
 
     if(json_resources.count("/CropBox"))
@@ -173,8 +173,12 @@ namespace pdflib
       }
     else
       {
-        LOG_S(FATAL) << "could not find the page-dimensions: " 
-                     << json_resources.dump(4);
+	std::stringstream ss;
+	ss << "could not find the page-dimensions: " 
+	   << json_resources.dump(4);
+	
+        LOG_S(ERROR) << ss.str();
+	throw std::logic_error(ss.str());
       }
   }
 

{docling_parse-2.0.2 → docling_parse-2.0.4}/src/v2/pdf_resources/page_font/base_font.h

@@ -157,9 +157,15 @@ namespace pdflib
 	return bbox[3];
       }
 
-    LOG_S(FATAL) << "properties does not have key 'Ascender': " 
-                 << properties.dump(2);
-
+    {
+      std::stringstream ss;
+      ss << "properties does not have key 'Ascender': " 
+	 << properties.dump(2);
+      
+      LOG_S(ERROR) << ss.str();
+      throw std::logic_error(ss.str());
+    }
+    
     return -1.;
   }
 
@@ -179,9 +185,15 @@ namespace pdflib
 	return bbox[1];
       }
 
-    LOG_S(FATAL) << "properties does not have key 'Descender': " 
-                 << properties.dump(2);
+    {
+      std::stringstream ss;
+      ss << "properties does not have key 'Descender': " 
+	 << properties.dump(2);
 
+      LOG_S(ERROR) << ss.str();
+      throw std::logic_error(ss.str());
+    }
+    
     return -1.;
   }
 
@@ -194,9 +206,15 @@ namespace pdflib
         return properties["FontBBox"].get<std::array<double, 4> >();
       }
 
-    LOG_S(FATAL) << "properties does not have key 'FontBBox': " 
-                 << properties.dump(2);
-
+    {
+      std::stringstream ss;
+      ss << "properties does not have key 'FontBBox': " 
+	 << properties.dump(2);
+      
+      LOG_S(ERROR) << ss.str();
+      throw std::logic_error(ss.str());
+    }
+    
     return {0.0, 0.0, 0.0, 0.0};
   }
 

{docling_parse-2.0.2 → docling_parse-2.0.4}/src/v2/pdf_resources/page_font/base_fonts.h

@@ -121,8 +121,6 @@ namespace pdflib
       {
         if(norm_name.find(itr->first)!=std::string::npos)
           {	    
-            //return itr->first;
-
 	    // we have to be careful that "Helvetica" is not returned for Helvetice-Bold!
 	    if(result.size()<(itr->first).size())
 	      {
@@ -136,8 +134,8 @@ namespace pdflib
 	return result;
       }
 
-    LOG_S(FATAL) << "unkown " << font_name << "[norm_name=" << norm_name << "]";
-
+    LOG_S(ERROR) << "unkown " << font_name << "[norm_name=" << norm_name << "]";
+    
     return "Unknown";
   }
 
@@ -269,7 +267,11 @@ namespace pdflib
 
     if(fontname=="unknown")
       {
-        LOG_S(FATAL) << "no FontName found in " << filename;
+	std::stringstream ss;
+	ss << "no FontName found in " << filename;
+	
+        LOG_S(ERROR) << ss.str();
+	throw std::logic_error(ss.str());
       }
 
     return fontname;