Add references field to yaml input standard

SConstruct

@@ -1589,6 +1589,32 @@ for yaml in mglob(env, "data", "yaml"):
     dest = pjoin("build", "data", yaml.name)
     build(env.Command(dest, yaml.path, Copy("$TARGET", "$SOURCE")))
 
+# Copy Chemkin input files
+ck_sources = [
+    dict(input='data/inputs/gri30.inp',
+         thermo='data/thermo/gri30_thermo.dat',
+         transport='data/transport/gri30_tran.dat',
+         bibtex='data/bibtex/gri30.bib'),
+    dict(input='data/inputs/air.inp',
+         transport='data/transport/gri30_tran.dat'),
+    dict(input='data/inputs/argon.inp',
+         thermo='data/thermo/gri30_thermo.dat',
+         transport='data/transport/gri30_tran.dat'),
+    dict(input='data/inputs/airNASA9.inp',
+         thermo='data/thermo/airDataNASA9.dat',
+         bibtex='data/bibtex/nasa9.bib'),
+    dict(input='data/inputs/h2o2.inp',
+         transport='data/transport/gri30_tran.dat'),
+    dict(thermo='data/thermo/nasathermo.dat',
+         bibtex='data/bibtex/nasa7.bib')
+]
+
+for mech in ck_sources:
+    for key in ['input', 'thermo', 'transport', 'bibtex']:
+        if key in mech:
+            build(env.Command('build/chemkin/{}'.format(mech[key].split('/')[-1]),
+                              mech[key], Copy('$TARGET', '$SOURCE')))
+
 if addInstallActions:
     # Put headers in place
     headerBase = 'include/cantera'

data/bibtex/gri30.bib

@@ -0,0 +1,9 @@
+@misc{gri30,
+    title = "GRI-Mech 3.0",
+    author = "Gregory P. Smith and David M. Golden and Michael Frenklach and
+              Nigel W. Moriarty and Boris Eiteneer and Mikhail Goldenberg and
+              C. Thomas Bowman and Ronald K. Hanson and Soonho Song and
+              William C. {Gardiner Jr.} and Vitali V. Lissianski and Zhiwei Qin",
+    year = 1999,
+    howpublished = "\url{http://combustion.berkeley.edu/gri-mech/version30/text30.html}"
+}

data/bibtex/nasa7.bib

@@ -0,0 +1,20 @@
+@misc{nasa7,
+    title = "NASA thermodynamic database",
+    note = "7-term polynomial coefficients in 1971 format",
+    howpublished = "\url{https://shepherd.caltech.edu/EDL/PublicResources/sdt/cti/NASA7/nasa7.dat}"
+}
+@techreport{gordon1971,
+    title = "Computer Program for Calculation of Complex Chemical Equilibrium
+             Composition, Rocket Performance, Incident and Reflected Shocks and
+             Chapman-Jouguet Detonations",
+    author = "S. Gordon and B. J. McBride",
+    year = 1971,
+    number = "NASA SP-273"
+}
+@techreport{mcbride1993,
+    title = "Coefficients for Calculating Thermodynamic and Transport Properties
+             of Individual Species",
+    author = "B. J. McBride and S. Gordon and M. A. Reno",
+    year = 1993,
+    number = "NASA TM-4513"
+}

data/bibtex/nasa9.bib

@@ -0,0 +1,12 @@
+@misc{nasa9,
+    title = "NASA thermodynamic database",
+    note = "9-term coefficients in 1996 format",
+    howpublished = "\url{https://shepherd.caltech.edu/EDL/PublicResources/sdt/cti/NASA7/nasa7.dat}"
+}
+@techreport{mcbride2002,
+    title = "Nasa Glenn coefficients for Calculating Thermodynamic Properties
+             of Individual Species",
+    author = "B. J. McBride and M. J. Zehe and S. Gordon",
+    year = 2002,
+    number = "NASA TP2002-211556"
+}

data/inputs/air.inp

@@ -1,3 +1,5 @@
+! Ideal gas properties of air. Includes several reactions among
+! the included species.
 ELEMENTS
 O  N  AR
 END

data/inputs/argon.inp

@@ -1,3 +1,5 @@
+! Pure argon phase. Thermo and transport properties are taken
+! from GRI-Mech 3.0.
 ELEMENTS
 AR
 END

data/inputs/h2o2.inp

@@ -1,3 +1,4 @@
+! Hydrogen-Oxygen submechanism extracted from GRI-Mech 3.0.
 ELEMENTS
 O  H  AR
 END

data/inputs/silane.inp

@@ -1,3 +1,5 @@
+! Source unknown. Data originially added by Dave Goodwin in an early
+! version of Cantera.
 ELEMENTS
 SI H HE 
 END

data/thermo/nasathermo.dat

@@ -1,5 +1,3 @@
-THERMO NO_TMID
- 300.0   1000.0   5000.0
 !
 ! This is the NASA thermodynamic database, which is available for download
 ! from http://www.galcit.caltech.edu/EDL/public/thermo.html. The original 
@@ -14,6 +12,8 @@ THERMO NO_TMID
 ! Report TM-4513, October 1993.
 !-----------------------------------------------------------------------------
 !
+THERMO NO_TMID
+ 300.0   1000.0   5000.0
 Electron gas      L10/92E  1.   0.   0.   0.G   200.000  6000.0005.48579903-04 1
  2.50000000E+00 0.00000000E+00 0.00000000E+00 0.00000000E+00 0.00000000E+00    2
 -7.45375000E+02-1.17246902E+01 2.50000000E+00 0.00000000E+00 0.00000000E+00    3

interfaces/cython/SConscript

@@ -26,6 +26,10 @@ testFiles = localenv.RecursiveInstall('#interfaces/cython/cantera/test/data',
                                       '#test/data')
 build(testFiles)
 
+ckFiles = localenv.RecursiveInstall('#interfaces/cython/cantera/examples/input',
+                                    '#build/chemkin')
+build(ckFiles)
+
 inputFiles = ['inputs/h2o2.inp', 'inputs/gri30.inp',
               'transport/gri30_tran.dat', 'thermo/gri30_thermo.dat']
 for f in inputFiles:
@@ -96,6 +100,7 @@ for f in (mglob(localenv, 'cantera', 'py') +
           mglob(localenv, 'cantera/examples/reactors', 'py') +
           mglob(localenv, 'cantera/examples/onedim', 'py') +
           mglob(localenv, 'cantera/examples/surface_chemistry', 'py') +
+          mglob(localenv, 'cantera/examples/input', 'py') +
           mglob(localenv, 'cantera/examples/misc', 'py')):
     localenv.Depends(mod, f)
 

interfaces/cython/cantera/ck2yaml.py

@@ -13,6 +13,7 @@
             [--transport=<filename>]
             [--surface=<filename>]
             [--name=<name>]
+            [--bibtex=<filename>]
             [--output=<filename>]
             [--permissive]
             [-d | --debug]
@@ -32,8 +33,10 @@
 'surface'.
 
 The '--permissive' option allows certain recoverable parsing errors (e.g.
-duplicate transport data) to be ignored. The '--name=<name>' option
-is used to override default phase names (i.e. 'gas').
+duplicate transport data) to be ignored. Further, the '--name=<name>' option
+is used to override default phase names (i.e. 'gas'). The '--bibtex=<filename>'
+option attaches references to the yaml output, where fields are based on BibTeX
+style input.
 """
 
 from collections import defaultdict, OrderedDict
@@ -742,7 +745,8 @@ def __init__(self):
         self.species_dict = {}  # bulk and surface species
         self.surfaces = []
         self.reactions = []
-        self.headerLines = []
+        self.header_lines = []
+        self.bibtex = {}  # for bibtex entries
         self.files = []  # input file names
 
     def warn(self, message):
@@ -1328,6 +1332,86 @@ def parse_expression(expression, dest):
 
         return reaction, revReaction
 
+    def load_bibtex_file(self, path):
+        """
+        Load and separate BibTeX-formatted entries from ``path`` on disk.
+        """
+        def text_strip(text):
+            text = text.strip()
+            if text[0] == '"' and text[-1] == '"':
+                return text.strip('"')
+            elif text[0] == '{' and text[-1] == '}':
+                return text.strip('{}')
+            elif text.isdigit():
+                return text
+            else:
+                raise NotImplementedError(
+                    "Cannot parse '{}': this minimal BibTeX parser does not "
+                    "support @string definitions and otherwise adheres to the "
+                    "BibTeX format as described in "
+                    "http://www.bibtex.org/Format/".format(text))
+
+        def parse_citation(entry):
+            # split entry into tagged key/value blocks and retrieve entry type
+            blocks = '\n'.join([e.strip() for e in entry[1:]])
+            blocks = blocks.rstrip('}').rstrip(',\n ').split(',\n')
+            out = {'entry_type': entry[0].split('{')[0].strip(' ').lower()}
+
+            for block in blocks:
+                # retrieve key
+                parts = block.split('=')
+                key = parts[0].strip().lower()
+                block = '='.join(parts[1:])
+
+                # build value
+                try:
+                    value = ''.join([text_strip(b)
+                                    for b in block.replace('\n', ' ').split('#')])
+                except NotImplementedError as err:
+                    raise InputError("Encountered invalid syntax in "
+                        "BibTeX entry:\n{}".format('\n'.join(entry))) from err
+
+                # reformat author list
+                if key == 'author':
+                    authors = [a.strip().replace('{', '').replace('}', '')
+                              for a in value.split(' and ')]
+                    if len(authors) > 1:
+                        value = ', '.join(authors[:-1]) + ' and ' + authors[-1]
+
+                out[key] = value if len(value) > 1 else value[0]
+            return out
+
+        def read_citation(bib_file):
+            entry = []
+            count = 0
+            while not(entry) or count > 0:
+                line = strip_nonascii(bib_file.readline()).rstrip()
+                count += line.count('{') - line.count('}')
+                count -= line.count('\{') - line.count('\}')
+                entry.append(line)
+                if line == "":
+                    break
+
+            if entry[0]:
+                regex = r"^@+([a-zA-z]+){+([ A-Za-z0-9_-]+)[ ,]"
+                bib = re.findall(regex, entry[0].strip())
+                if bib and entry[-1].rstrip()[-1] == '}' and count == 0:
+                    return bib[0][1].strip(), parse_citation(entry)
+                else:
+                    raise InputError("Encountered invalid syntax in "
+                        "BibTeX entry:\n{}".format('\n'.join(entry)))
+            else:
+                return None, None
+
+        with open(path, 'r', errors='ignore') as bib_file:
+
+            while True:
+                label, entry = read_citation(bib_file)
+                if label is not None:
+                    self.bibtex[label] = entry
+                else:
+                    break
+
     def load_chemkin_file(self, path, skip_undeclared_species=True, surface=False):
         """
         Load a Chemkin-format input file from ``path`` on disk.
@@ -1356,7 +1440,7 @@ def readline():
             while line is not None:
                 tokens = line.split() or ['']
                 if inHeader and not line.strip():
-                    self.headerLines.append(comment.rstrip())
+                    self.header_lines.append(comment.rstrip())
 
                 if tokens[0].upper().startswith('ELEM'):
                     inHeader = False
@@ -1839,12 +1923,33 @@ def write_yaml(self, name='gas', out_name='mech.yaml'):
                     n_reacting_phases += 1
 
             # header from original file
-            desc = '\n'.join(line.rstrip() for line in self.headerLines)
+            desc = '\n'.join(line.rstrip() for line in self.header_lines)
             desc = desc.strip('\n')
             desc = textwrap.dedent(desc)
             if desc.strip():
                 emitter.dump({'description': yaml.scalarstring.PreservedScalarString(desc)}, dest)
 
+            # bibtex entries
+            if self.bibtex:
+                entries = BlockMap()
+                for key, val in self.bibtex.items():
+                    tags = []
+                    comment = val.pop('entry_type')
+                    for k, v in val.items():
+                        if v.isdigit():
+                            out = int(v)
+                        elif not v.count(" ") and len(v) > 50:
+                            out = yaml.scalarstring.PreservedScalarString(v)
+                        else:
+                            out = v
+                        tags.append((k, out))
+                    entries[key] = BlockMap(tags)
+                    entries.yaml_add_eol_comment(comment, key)
+                bib = BlockMap([('references', entries)])
+                if desc.strip():
+                    bib.yaml_set_comment_before_after_key('references', before='\n')
+                emitter.dump(bib, dest)
+
             # Additional information regarding conversion
             files = [os.path.basename(f) for f in self.files]
             metadata = BlockMap([
@@ -1853,7 +1958,7 @@ def write_yaml(self, name='gas', out_name='mech.yaml'):
                 ('cantera-version', '2.5.0a3'),
                 ('date', formatdate(localtime=True)),
             ])
-            if desc.strip():
+            if desc.strip() or self.bibtex:
                 metadata.yaml_set_comment_before_after_key('generator', before='\n')
             emitter.dump(metadata, dest)
 
@@ -1946,8 +2051,8 @@ def write_yaml(self, name='gas', out_name='mech.yaml'):
 
     @staticmethod
     def convert_mech(input_file, thermo_file=None, transport_file=None,
-                     surface_file=None, phase_name='gas', out_name=None,
-                     quiet=False, permissive=None):
+                     surface_file=None, phase_name='gas', bibtex_file=None,
+                     out_name=None, quiet=False, permissive=None):
 
         parser = Parser()
         if quiet:
@@ -2013,6 +2118,19 @@ def convert_mech(input_file, thermo_file=None, transport_file=None,
                                 surface_file, parser.line_number, err))
                 raise
 
+        if bibtex_file:
+            parser.files.append(bibtex_file)
+            bibtex_file = os.path.expanduser(bibtex_file)
+            if not os.path.exists(bibtex_file):
+                raise IOError('Missing input file: {0!r}'.format(bibtex_file))
+            try:
+                # Read input mechanism files
+                parser.load_bibtex_file(bibtex_file)
+            except Exception as err:
+                logging.warning("\nERROR: Unable to parse '{0}':\n{1}\n".format(
+                                bibtex_file, err))
+                raise
+
         if out_name:
             out_name = os.path.expanduser(out_name)
         else:
@@ -2027,15 +2145,16 @@ def convert_mech(input_file, thermo_file=None, transport_file=None,
         return surface_names
 
 
-def convert_mech(input_file, thermo_file=None, transport_file=None, surface_file=None,
-                 phase_name='gas', out_name=None, quiet=False, permissive=None):
+def convert_mech(input_file, thermo_file=None, transport_file=None,
+                 surface_file=None, phase_name='gas', bibtex_file=None,
+                 out_name=None, quiet=False, permissive=None):
     return Parser.convert_mech(input_file, thermo_file, transport_file, surface_file,
-                               phase_name, out_name, quiet, permissive)
+                               phase_name, bibtex_file, out_name, quiet, permissive)
 
 def main(argv):
 
     longOptions = ['input=', 'thermo=', 'transport=', 'surface=', 'name=',
-                   'output=', 'permissive', 'help', 'debug', 'quiet',
+                   'bibtex=', 'output=', 'permissive', 'help', 'debug', 'quiet',
                    'no-validate', 'id=']
 
     try:
@@ -2077,6 +2196,13 @@ def main(argv):
               ' must be provided.\nRun "ck2yaml.py --help" to see usage help.')
         sys.exit(1)
 
+    if '--bibtex' in options:
+        bibtex_file = options['--bibtex']
+        if not bibtex_file.endswith('.bib'):
+            bibtex_file += '.bib'
+    else:
+        bibtex_file = None
+
     if '--output' in options:
         out_name = options['--output']
         if not out_name.endswith('.yaml') and not out_name.endswith('.yml'):
@@ -2087,8 +2213,8 @@ def main(argv):
         out_name = os.path.splitext(thermo_file)[0] + '.yaml'
 
     surfaces = Parser.convert_mech(input_file, thermo_file, transport_file,
-                                   surface_file, phase_name, out_name,
-                                   quiet, permissive)
+                                   surface_file, phase_name, bibtex_file,
+                                   out_name, quiet, permissive)
 
     # Do full validation by importing the resulting mechanism
     if not input_file: