[ctml2yaml] Fix several XML parsing errors

The Python Expat parser requires that the <?xml version...> tag occur as
the first characters in the file, even before any blank space, so lstrip
is used to remove any whitespace. In addition, raw & characters are
replaced with their escaped version.

interfaces/cython/cantera/ctml2yaml.py

@@ -2122,7 +2122,20 @@ def create_phases_from_data_node(
 def convert(inpfile: Union[str, Path], outfile: Union[str, Path]):
     """Convert an input CTML file to a YAML file."""
     inpfile = Path(inpfile)
-    ctml_tree = etree.parse(str(inpfile)).getroot()
+    ctml_text = inpfile.read_text().lstrip()
+    # Replace any raw ampersands in the text with an escaped ampersand. This
+    # substitution is necessary because ctml_writer outputs literal & characters
+    # from text data into the XML output. Although this doesn't cause a problem
+    # with the custom XML parser in Cantera, standards-compliant XML parsers
+    # like the Expat one included in Python can't handle the raw & character. I
+    # could not figure out a way to override the parsing logic such that & could
+    # be escaped in the data during parsing, so it has to be done manually here.
+    # According to https://stackoverflow.com/a/1091953 there are 5 escaped
+    # characters in XML: " (&quot;), ' (&apos;), & (&amp;), < (&lt;), and >
+    # (&gt;). This code only replaces & not followed by one of the escaped
+    # character codes.
+    ctml_text = re.sub("&(?!amp;|quot;|apos;|lt;|gt;)", "&amp;", ctml_text)
+    ctml_tree = etree.fromstring(ctml_text)
 
     species_data = create_species_from_data_node(ctml_tree)
     reaction_data = create_reactions_from_data_node(ctml_tree)

test/data/species-names.xml

@@ -8,7 +8,7 @@
     <speciesArray datasrc="#species_data">
       (Parens)      @#$%^-2       co:lons:      [xy2]*{.}
       plus+         eq=uals       plus          trans_butene
-      co</speciesArray>
+      co amp&ersand</speciesArray>
     <reactionArray datasrc="#reaction_data"/>
     <state>
       <temperature units="K">300.0</temperature>
@@ -175,6 +175,24 @@
         </NASA>
       </thermo>
     </species>
+
+    <!-- species amp&ersand    -->
+    <species name="amp&ersand">
+      <atomArray>C:1 H:4 </atomArray>
+      <note>Contains a raw & character</note>
+      <thermo>
+        <NASA Tmin="200.0" Tmax="1000.0" P0="100000.0">
+           <floatArray size="7" name="coeffs">
+             5.149876130E+00,  -1.367097880E-02,   4.918005990E-05,  -4.847430260E-08, 
+             1.666939560E-11,  -1.024664760E+04,  -4.641303760E+00</floatArray>
+        </NASA>
+        <NASA Tmin="1000.0" Tmax="3500.0" P0="100000.0">
+           <floatArray size="7" name="coeffs">
+             7.485149500E-02,   1.339094670E-02,  -5.732858090E-06,   1.222925350E-09, 
+             -1.018152300E-13,  -9.468344590E+03,   1.843731800E+01</floatArray>
+        </NASA>
+      </thermo>
+    </species>
   </speciesData>
   <reactionData id="reaction_data">
 
@@ -366,5 +384,19 @@
       <reactants>co:1.0 co:lons::1</reactants>
       <products>plus+:2.0</products>
     </reaction>
+
+    <!-- reaction 0013    -->
+    <reaction id="0013" reversible="yes">
+      <equation>amp&ersand [=] plus+</equation>
+      <rateCoeff>
+        <Arrhenius>
+           <A>9.999000E+06</A>
+           <b>9.9</b>
+           <E units="cal/mol">999.900000</E>
+        </Arrhenius>
+      </rateCoeff>
+      <reactants>amp&ersand:1.0</reactants>
+      <products>plus+:1.0</products>
+    </reaction>
   </reactionData>
 </ctml>