Expose CDX support to FileParsers and ChemDraw to SWIG (#8681)

* Fist pass at CDX support

* Enable CDX support for reading (also) in the CDXMLParser API

* Add cdxml test files

* Update swig wrappers for CDXMLFormat and Parameters

* Add constructor to ChemDrawParserParams

* Add Java SWIG support for ChemDraw

* Add chemdraw define to rdconfig

* Add missing chemdraw deps

* Remove direct expat link

* Fix Java linkages for ChemDraw

* Remove bad merge code

* Remove bad merge code

* Fix csharp builds

* Add sniffer for the ChemDraw DataStream

* Include filesystem

* Fix test on windows

* Add more CDX tests

* Ensure streams are open in binary mode to support CDX on windows

* Fix text to show that a Block is the text input, not a file

* Fix CSharp test

* Disable CDX tests when not building chemdraw

* Turn back on chemdraw

* Response to review

* Turn off chemdraw support for the limited external test

---------

Co-authored-by: Brian Kelley <bkelley@glysade.com>

External/ChemDraw/Wrap/rdChemDraw.cpp

@@ -70,7 +70,8 @@ python::object MolsFromChemDrawBlockHelper(const std::string &filename, bool san
                                  bool removeHs) {
   std::vector<std::unique_ptr<RWMol>> mols;
   try {
-    mols = RDKit::v2::MolsFromChemDrawBlock(filename, {sanitize, removeHs});
+    mols = RDKit::v2::MolsFromChemDrawBlock(filename,
+					    {sanitize, removeHs, RDKit::v2::CDXFormat::CDXML});
   } catch (RDKit::BadFileException &e) {
     PyErr_SetString(PyExc_IOError, e.what());
     throw python::error_already_set();
@@ -89,7 +90,8 @@ python::object MolsFromChemDrawBlockHelper(const std::string &filename, bool san
 
 python::tuple MolsFromChemDrawFileHelper(python::object cdxml, bool sanitize,
                             bool removeHs) {
-  auto mols = RDKit::v2::MolsFromChemDrawFile(pyObjectToString(cdxml), {sanitize, removeHs});
+  auto mols = RDKit::v2::MolsFromChemDrawFile(pyObjectToString(cdxml),
+					      {sanitize, removeHs, RDKit::v2::CDXFormat::CDXML});
   python::list res;
   for (auto &mol : mols) {
     // take ownership of the data from the unique_ptr

External/ChemDraw/chemdraw.cpp

@@ -237,8 +237,41 @@ void visit_children(
   }
 }
 
+CDXFormat sniff_format(std::istream &is) {
+    // Remember the current read position
+    std::streampos start_pos = is.tellg();
+    if (start_pos == -1) {
+        // Some streams (like std::cin) may not support tellg
+      return CDXFormat::AUTO; // here it simply means we failed
+    }
+
+    // CDX header consists of:
+    // 8 bytes with the value "VjCD0100" (hex: 56 6A 43 44 30 31 30 30).
+    CDXFormat format = CDXFormat::CDXML;
+    const std::vector<char> header{86, 106, 67, 68, 48, 49, 48, 48};
+    std::vector<char> buf(8);
+    is.read(buf.data(), 8);
+    if (buf == header) {
+      format = CDXFormat::CDX;
+    }
+    
+    // Reset the stream position
+    is.clear(); // clear EOF flag if we hit it
+    is.seekg(start_pos);
+    return format;
+}
+  
 std::unique_ptr<CDXDocument> streamToCDXDocument(std::istream &inStream,
                                                  CDXFormat format) {
+  if(format == CDXFormat::AUTO) {
+    format = sniff_format(inStream);
+    if(format == CDXFormat::AUTO) {
+      const std::string msg = " Failed deducing whether the input stream is CDXML or CDX";
+      BOOST_LOG(rdErrorLog) << msg << std::endl;
+      throw FileParseException(msg);
+    }
+  }
+  
   if (format == CDXFormat::CDXML) {
     CDXMLParser parser;
     // populate tree structure pt
@@ -249,17 +282,21 @@ std::unique_ptr<CDXDocument> streamToCDXDocument(std::istream &inStream,
                                           static_cast<int>(data.size()),
                                           HaveAllXml)) {
       auto error = XML_GetErrorCode(parser);
-      BOOST_LOG(rdErrorLog) << "Failed parsing XML with error code " << error;
-      throw FileParseException("Bad Input File");
+      std::stringstream msg;
+      msg << "Failed parsing XML with error code " << error;
+      BOOST_LOG(rdErrorLog) << msg.str() << std::endl;
+      throw FileParseException(msg.str());
     }
 
     return parser.ReleaseDocument();
   } else {
-    throw FileParseException("Can't handle cdx yet");
-    return std::unique_ptr<CDXDocument>();
+    CDXistream input(inStream);
+    const bool doThrow = true;
+    std::unique_ptr<CDXDocument> doc(CDXReadDocFromStorage(input, doThrow));
+    return doc;
   }
 }
-
+ 
 // may raise FileParseException
 std::vector<std::unique_ptr<RWMol>> molsFromCDXMLDataStream(
     std::istream &inStream, const ChemDrawParserParams &params) {

External/ChemDraw/chemdraw.h

@@ -41,13 +41,18 @@ namespace RDKit {
 namespace v2 {
 enum class CDXFormat {
   CDX = 1,
-  CDXML = 2
+  CDXML = 2,
+  AUTO = 3
 };
 
 struct RDKIT_RDCHEMDRAWLIB_EXPORT ChemDrawParserParams {
-  bool sanitize = true;
-  bool removeHs = true;
-  CDXFormat format = CDXFormat::CDXML;
+  bool sanitize;
+  bool removeHs;
+  CDXFormat format;
+  ChemDrawParserParams() : sanitize(true), removeHs(true), format(CDXFormat::AUTO) {}
+  ChemDrawParserParams(bool sanitize, bool removeHs, CDXFormat format) :
+     sanitize(sanitize), removeHs(removeHs), format(format) {}
+  
 };
 
 std::vector<std::unique_ptr<RWMol>> RDKIT_RDCHEMDRAWLIB_EXPORT