Changeset 42

Timestamp:

Aug 11, 2010, 4:09:24 PM (11 years ago)

Author:

j@…

bzr:base-revision:

j@dannynavarro.net-20100809124849-61iz4u0uppej4zrn

bzr:committer:

Danny Navarro <j@dannynavarro.net>

bzr:file-ids:

mzcms/parsers.py parsers.py-20100806092910-g1sxvv1o5b9umkof-1

bzr:mapping-version:

v4

bzr:repository-uuid:

724254b2-fbe6-419d-9466-c04ef4c9d29d

bzr:revision-id:

j@dannynavarro.net-20100809132407-1fe2wb5blanid09e

bzr:revno:

42

bzr:revprop:branch-nick:

trunk

bzr:root:

trunk

bzr:timestamp:

2010-08-09 15:24:07.388000011 +0200

bzr:user-agent:

bzr2.1.2+bzr-svn1.0.3

svn:original-date:

2010-08-09T13:24:07.388000Z

Message:

Added parse method for summary section

File:

• trunk/mzcms/parsers.py (modified) (5 diffs)

trunk/mzcms/parsers.py

@@ -80 +80 @@
                 else:
                     return frag_line
+
+    def _parse_summary(self, dat_file):
+        """Parse summary section
+        """
+        summspec = list()
+        summary_section = SECTION_TEMPLATE.substitute(section="summary")
+        for line in dat_file:
+            if line.strip() == summary_section:
+                break
+        for line in dat_file:
+            if line.startswith('qexp'):
+                r_mz, r_charge = line.strip().split('=')[1].split(',')
+                mz = float(r_mz)
+                charge = int(r_charge.rstrip('+'))
+                summspec.append((mz, charge))
+        return summspec
 
     def _parse_psms(self, dat_file):
@@ -117 +133 @@
                 return nativeid_psms
 
-    def _parse_spectra(self, datfile):
+    def _parse_spectra(self, dat_file):
         """Gets the data coming from the input file from Mascot dat
            format
@@ -123 +139 @@
         nativeid_spectra = defaultdict(dict)
         nativeid = 1
-        for line in datfile:
+        for line in dat_file:
             nativeid_str = ''.join(("query", str(nativeid)))
             query_line = SECTION_TEMPLATE.substitute(section=nativeid_str)
@@ -131 +147 @@
             elif line.startswith("title="):
                 line = line.strip()
-                #TODO: handle fractions
-                #fraction = int(re.search(fraction_regex, line).group(1))
-                #current_id_mgf["Fraction"] = fraction
                 try:
-                    quoted_rawfn = re.search(rawfn_regex, line).group(1)
+                    quoted_rawfn = re.search(self.rawfn_regex, line).group(1)
                 except AttributeError:
                     sys.exit("It seems there is no raw: field in TITLE")
@@ -160 +173 @@
         pkl_fn = self._parse_spectra_fn(dat_file)
         frag_mode = self._parse_frag_mode(dat_file)
+        summspec = self._parse_summary(dat_file)
         nativeid_psms = self._parse_psms(dat_file)
-        import ipdb; ipdb.set_trace()
-        nativeid_spectra = self._parse_spectra(dat_file)
+        extraspec = self._parse_spectra(dat_file)
         for native_id, psms in nativeid_psms.items():
             for psm in psms: