docling-parse 2.0.3__tar.gz → 2.0.4__tar.gz

{docling_parse-2.0.3 → docling_parse-2.0.4}/CHANGELOG.md

@@ -1,3 +1,9 @@
+## [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

{docling_parse-2.0.3 → docling_parse-2.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling-parse
-Version: 2.0.3
+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-2.0.3 → 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-2.0.3 → docling_parse-2.0.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling-parse"
-version = "2.0.3"
+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-2.0.3 → docling_parse-2.0.4}/src/v2/pdf_resources/page_font/cmap.h

@@ -15,7 +15,7 @@ namespace pdflib
     ~cmap_parser();
 
     std::map<uint32_t, std::string> get() { return _map; }
-    
+
     void print();
 
     void parse(std::vector<qpdf_instruction>& instructions);
@@ -77,7 +77,7 @@ namespace pdflib
   {
     for(auto itr=_map.begin(); itr!=_map.end(); itr++)
       {
-	LOG_S(INFO) << itr->first << "\t" << itr->second;
+        LOG_S(INFO) << itr->first << "\t" << itr->second;
       }
   }
 
@@ -141,8 +141,8 @@ namespace pdflib
     std::string unparsed = handle.unparse();
 
     // we have a hex-string ...
-    if(unparsed.size()>0 and 
-       unparsed.front()=='<' and 
+    if(unparsed.size()>0 and
+       unparsed.front()=='<' and
        unparsed.back()=='>')
       {
         unparsed = unparsed.substr(1, unparsed.size()-2);
@@ -170,14 +170,20 @@ namespace pdflib
   {
     //logging_lib::info("pdf-parser") << __FUNCTION__ << "\n";
 
-    // FIXME this might be too short
-    std::string result(64, ' ');
-
-    assert(handle.isString());
+    //assert(handle.isString());
+    if(not handle.isString())
+      {
+        std::string message = "not handle.isString()";
+        LOG_S(ERROR) << message;
+        throw std::logic_error(message);
+      }
 
     std::string unparsed = handle.unparse();
     //logging_lib::info("pdf-parser") << "unparsed : " << unparsed << "\n";
 
+    // FIXME this might be too short
+    std::string result(64, ' ');
+
     // we have a hex-string ...
     if(unparsed.size()>0     and
        unparsed.front()=='<' and
@@ -252,7 +258,20 @@ namespace pdflib
   void cmap_parser::parse_begincodespacerange(std::vector<qpdf_instruction>& parameters)
   {
     LOG_S(INFO) << __FUNCTION__;
-    assert(parameters.size()==1);
+
+    //assert(parameters.size()==1);
+
+    const int num_params = 1;
+    if(parameters.size()<num_params)
+      {
+        std::string message = "parameters.size() < " + std::to_string(num_params);
+        LOG_S(ERROR) << message;
+        throw std::logic_error(message);
+      }
+    else if(parameters.size()>num_params)
+      {
+        LOG_S(WARNING) << "parameters.size() > " << num_params;
+      }
 
     csr_cnt = parameters[0].to_int();
   }
@@ -260,7 +279,19 @@ namespace pdflib
   void cmap_parser::parse_endcodespacerange(std::vector<qpdf_instruction>& parameters)
   {
     LOG_S(INFO) << __FUNCTION__;
-    assert(parameters.size()==2*csr_cnt);
+    //assert(parameters.size()==2*csr_cnt);
+
+    const int num_params = 2;
+    if(parameters.size()<num_params)
+      {
+        std::string message = "parameters.size() < " + std::to_string(num_params);
+        LOG_S(ERROR) << message;
+        throw std::logic_error(message);
+      }
+    else if(parameters.size()>num_params)
+      {
+        LOG_S(WARNING) << "parameters.size() > " << num_params;
+      }
 
     csr_range.first  = cmap_parser::to_uint32(parameters[0].obj);
     csr_range.second = cmap_parser::to_uint32(parameters[1].obj);
@@ -271,8 +302,20 @@ namespace pdflib
 
   void cmap_parser::parse_beginbfrange(std::vector<qpdf_instruction>& parameters)
   {
-    assert(parameters.size()==1);
     LOG_S(INFO) << __FUNCTION__;
+    //assert(parameters.size()==1);
+
+    const int num_params = 1;
+    if(parameters.size()<num_params)
+      {
+        std::string message = "parameters.size() < " + std::to_string(num_params);
+        LOG_S(ERROR) << message;
+        throw std::logic_error(message);
+      }
+    else if(parameters.size()>num_params)
+      {
+        LOG_S(WARNING) << "parameters.size() > " << num_params;
+      }
 
     bf_cnt = parameters[0].to_int();
   }
@@ -285,11 +328,10 @@ namespace pdflib
     std::string result="";
     {
       std::string tmp = my_handle.getStringValue();
-      assert(tmp.size()==1 or tmp.size()==2);
+      //assert(tmp.size()==1 or tmp.size()==2);
 
       result = to_utf8(my_handle, tmp.size());
     }
-
     //LOG_S(INFO) << __FUNCTION__ << my_handle.unparse() << "\t" << source << "\t'" << result << "'";
 
     return result;
@@ -297,7 +339,7 @@ namespace pdflib
 
   // the target is always 2 byte
   std::string cmap_parser::get_target(QPDFObjectHandle my_handle)
-  {   
+  {
     std::string target = to_utf8(my_handle, 2);
 
     //LOG_S(INFO) << __FUNCTION__ << "\t" << my_handle.getStringValue() << "\t" << target;
@@ -308,7 +350,19 @@ namespace pdflib
   void cmap_parser::parse_endbfrange(std::vector<qpdf_instruction>& parameters)
   {
     LOG_S(INFO) << __FUNCTION__;
-    assert(parameters.size()==3*bf_cnt);
+    //assert(parameters.size()==3*bf_cnt);
+
+    const int num_params = 3*bf_cnt;
+    if(parameters.size()<num_params)
+      {
+        std::string message = "parameters.size() < " + std::to_string(num_params);
+        LOG_S(ERROR) << message;
+        throw std::logic_error(message);
+      }
+    else if(parameters.size()>num_params)
+      {
+        LOG_S(WARNING) << "parameters.size() > " << num_params;
+      }
 
     std::string source_start;
     std::string source_end;
@@ -331,10 +385,8 @@ namespace pdflib
 
             set_range(source_start, source_end, tmp);
           }
-        else
+        else if(target.isArray())
           {
-            assert(target.isArray());
-
             std::vector<QPDFObjectHandle> tmps = target.getArrayAsVector();
 
             std::vector<std::string> target_strs;
@@ -352,6 +404,10 @@ namespace pdflib
 
             set_range(source_start, source_end, target_strs);
           }
+        else
+          {
+            LOG_S(WARNING) << "could not interprete the target";
+          }
       }
   }
 
@@ -371,9 +427,9 @@ namespace pdflib
 
     if(not (csr_range.first<=c and c<=csr_range.second))
       {
-	LOG_S(ERROR) << c << " is going out of bounds: " << csr_range.first << "," << csr_range.second;
+        LOG_S(ERROR) << c << " is going out of bounds: " << csr_range.first << "," << csr_range.second;
       }
-    
+
     if(_map.count(c)==1)
       {
         LOG_S(ERROR) << "overwriting number cmap[" << c << "]: " << _map.at(c) << " with " << tgt;
@@ -393,7 +449,7 @@ namespace pdflib
 
     if(itr_beg!=src_begin.end())
       {
-        LOG_S(WARNING) << "itr_beg!=src_begin.end() --> errors might occur in the cmap: " 
+        LOG_S(WARNING) << "itr_beg!=src_begin.end() --> errors might occur in the cmap: "
                        << "'" << src_begin << "' -> " << begin;
       }
 
@@ -402,7 +458,7 @@ namespace pdflib
 
     if(itr_end!=src_end.end())
       {
-        LOG_S(WARNING) << "itr_end!=src_end.end() --> errors might occur in the cmap: " 
+        LOG_S(WARNING) << "itr_end!=src_end.end() --> errors might occur in the cmap: "
                        << "'" << src_end << "' -> " << end;;
       }
 
@@ -420,66 +476,82 @@ namespace pdflib
       {
         for(uint32_t i = 0; i < end - begin + 1; i++)
           {
-            assert(csr_range.first<=begin+i and begin+i<=csr_range.second);
+            //assert(csr_range.first<=begin+i and begin+i<=csr_range.second);
 
-              try
-                {
-                  std::string tmp(128, 0);
+            if(csr_range.first<=begin+i and begin+i<=csr_range.second)
+              {
+                try
                   {
-                    auto itr = tmp.begin();
-                    itr = utf8::append(begin+i, itr);
-
-                    tmp.erase(itr, tmp.end());
-                  }
-
-                  if(_map.count(begin+i)==1)
+                    std::string tmp(128, 0);
                     {
-                      LOG_S(WARNING) << "overwriting number c=" << begin+i;
+                      auto itr = tmp.begin();
+                      itr = utf8::append(begin+i, itr);
+
+                      tmp.erase(itr, tmp.end());
                     }
 
-                  _map[begin + i] = tmp;
-                }
-              catch(...)
-                {
-                  LOG_S(ERROR) << "invalid utf8 string";
+                    if(_map.count(begin+i)==1)
+                      {
+                        LOG_S(WARNING) << "overwriting number c=" << begin+i;
+                      }
 
-                  _map[begin + i] = "UNICODE<"+std::to_string(begin+i)+">";
-                }
+                    _map[begin + i] = tmp;
+                  }
+                catch(...)
+                  {
+                    LOG_S(ERROR) << "invalid utf8 string";
+
+                    _map[begin + i] = "UNICODE<"+std::to_string(begin+i)+">";
+                  }
+              }
+            else
+              {
+                LOG_S(WARNING) << "index " << begin+i << " is out of bounds ["
+                               << csr_range.first << ", " << csr_range.second << "]";
+              }
           }
       }
     else
       {
         for(uint32_t i = 0; i < end - begin + 1; i++)
           {
-            assert(csr_range.first<=begin+i and begin+i<=csr_range.second);
+            //assert(csr_range.first<=begin+i and begin+i<=csr_range.second);
 
-              try
-                {
-                  std::string tmp(128, 0);
+            if(csr_range.first<=begin+i and begin+i<=csr_range.second)
+              {
+                try
                   {
-                    auto itr = tmp.begin();
-                    for(auto tgt_uint: tgts)
-                      {
-                        itr = utf8::append(tgt_uint, itr);
-                      }
-                    tmp.erase(itr, tmp.end());
-                  }
-
-                  if(_map.count(begin+i)==1)
+                    std::string tmp(128, 0);
                     {
-                      LOG_S(ERROR) << "overwriting number c=" << begin+i;
+                      auto itr = tmp.begin();
+                      for(auto tgt_uint: tgts)
+                        {
+                          itr = utf8::append(tgt_uint, itr);
+                        }
+                      tmp.erase(itr, tmp.end());
                     }
 
-                  _map[begin + i] = tmp;
-                }
-              catch(...)
-                {
-                  LOG_S(ERROR) << "invalid utf8 string";
+                    if(_map.count(begin+i)==1)
+                      {
+                        LOG_S(ERROR) << "overwriting number c=" << begin+i;
+                      }
 
-                  _map[begin + i] = "UNICODE<"+std::to_string(begin+i)+">";
-                }
+                    _map[begin + i] = tmp;
+                  }
+                catch(...)
+                  {
+                    LOG_S(ERROR) << "invalid utf8 string";
 
-              tgts.back() += 1;
+                    _map[begin + i] = "UNICODE<"+std::to_string(begin+i)+">";
+                  }
+              }
+            else
+              {
+		LOG_S(WARNING) << "index " << begin+i << " is out of bounds ["
+                               << csr_range.first << ", " << csr_range.second << "]";
+              }
+
+            tgts.back() += 1;
           }
       }
 
@@ -499,12 +571,11 @@ namespace pdflib
 
     for(uint32_t i = 0; i < end - begin + 1; i++)
       {
-        assert(csr_range.first<=begin+i and 
-               begin+i<=csr_range.second);
+        //assert(csr_range.first<=begin+i and begin+i<=csr_range.second);
 
         if(_map.count(begin+i)==1)
           {
-            LOG_S(ERROR) << "overwriting number c=" << begin+i;
+            LOG_S(WARNING) << "overwriting number c=" << begin+i;
           }
 
         _map[begin + i] = tgt.at(i);
@@ -518,16 +589,16 @@ namespace pdflib
 
     if(parameters.size()==1)
       {
-	char_count = parameters[0].to_int();
+        char_count = parameters[0].to_int();
       }
     else if(parameters.size()>0)
       {
-	LOG_S(WARNING) << "parameters.size()>0 for parse_beginbfchar";
-	char_count = parameters[0].to_int();
-      }    
+        LOG_S(WARNING) << "parameters.size()>0 for parse_beginbfchar";
+        char_count = parameters[0].to_int();
+      }
     else
       {
-	LOG_S(ERROR) << "parameters.size()!=1 for parse_beginbfchar";
+        LOG_S(ERROR) << "parameters.size()!=1 for parse_beginbfchar";
       }
   }
 
@@ -537,20 +608,20 @@ namespace pdflib
 
     if(parameters.size()!=2*char_count)
       {
-	LOG_S(WARNING) << "parameters.size()!=2*char_count -> "
-		       << "parameters: " << parameters.size() << ", "
-		       << "char_count: " << char_count;
+        LOG_S(WARNING) << "parameters.size()!=2*char_count -> "
+                       << "parameters: " << parameters.size() << ", "
+                       << "char_count: " << char_count;
       }
     //assert(parameters.size()==2*char_count);
-    
+
     for(size_t i=0; i<char_count; i++)
       {
-	if(2*i>=parameters.size())
-	  {
-	    LOG_S(ERROR) << "going out of bounds: skipping parse_endbfchar";
-	    continue;
-	  }
-	
+        if(2*i>=parameters.size())
+          {
+            LOG_S(ERROR) << "going out of bounds: skipping parse_endbfchar";
+            continue;
+          }
+
         QPDFObjectHandle source_ = parameters[2*i+0].obj;
         QPDFObjectHandle target_ = parameters[2*i+1].obj;
 

{docling_parse-2.0.3 → docling_parse-2.0.4}/src/v2/pdf_resources/page_font/font_cid.h

@@ -86,9 +86,12 @@ namespace pdflib
 
     if(file.fail())
       {
-	LOG_S(ERROR) << "filename does not exists: " << filename;	
-
+	//LOG_S(ERROR) << "filename does not exists: " << filename;
+	std::stringstream ss;
+	ss << "filename does not exists: " << filename;
 	
+	LOG_S(ERROR) << ss.str();
+	throw std::logic_error(ss.str());
       }
 
     bool        cmap=false;
@@ -110,28 +113,37 @@ namespace pdflib
             auto itr = std::remove(items.begin(), items.end(), "");
             items.erase(itr, items.end());
 
-            assert(items.size()==3);
-            std::string hex_beg = items[0].substr(1, items[0].size()-2);
-            std::string hex_end = items[1].substr(1, items[1].size()-2);
-            std::string val     = items[2];
-
-            uint32_t beg = stoul(hex_beg, NULL, 16);
-            uint32_t end = stoul(hex_end, NULL, 16);
-            uint32_t ind = stoul(val    , NULL, 10);
-
-            //LOG_S(INFO) << "\t"
-            //<< hex_beg << " (=" << beg << ")\t"
-            //<< hex_end << " (=" << end << ")\t"
-            //<< val     << " (=" << ind << ")";
-
-            for(uint32_t i=beg; i<=end; i++)
-              {
-                cmap2cid[i] = ind;
-                ind += 1;
-              }
+            //assert(items.size()==3);
+	    if(items.size()==3)
+	      {
+		std::string hex_beg = items[0].substr(1, items[0].size()-2);
+		std::string hex_end = items[1].substr(1, items[1].size()-2);
+		std::string val     = items[2];
+
+		uint32_t beg = stoul(hex_beg, NULL, 16);
+		uint32_t end = stoul(hex_end, NULL, 16);
+		uint32_t ind = stoul(val    , NULL, 10);
+
+		//LOG_S(INFO) << "\t"
+		//<< hex_beg << " (=" << beg << ")\t"
+		//<< hex_end << " (=" << end << ")\t"
+		//<< val     << " (=" << ind << ")";
+		
+		for(uint32_t i=beg; i<=end; i++)
+		  {
+		    cmap2cid[i] = ind;
+		    ind += 1;
+		  }
+	      }
+	    else
+	      {
+		LOG_S(ERROR) << "items does not have the right size";
+	      }
           }
         else // ignore
-          {}
+          {
+	    LOG_S(WARNING) << "ignoring";
+	  }
       }
   }
 
@@ -175,7 +187,7 @@ namespace pdflib
                       }
                   }
               }
-            assert(col_inds.size()>0);
+            //assert(col_inds.size()>0);
 
             //for(auto col_ind:col_inds)
             //{