Changeset 43

Timestamp:

Aug 11, 2010, 4:09:41 PM (11 years ago)

Author:

j@…

bzr:base-revision:

j@dannynavarro.net-20100809132407-1fe2wb5blanid09e

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-20100809140009-s4lr753fe9u4cqvu

bzr:revno:

43

bzr:revprop:branch-nick:

trunk

bzr:root:

trunk

bzr:timestamp:

2010-08-09 16:00:09.927000046 +0200

bzr:user-agent:

bzr2.1.2+bzr-svn1.0.3

svn:original-date:

2010-08-09T14:00:09.927000Z

Message:

Parse extra section of spectra

File:

• trunk/mzcms/parsers.py (modified) (4 diffs)

trunk/mzcms/parsers.py

@@ -46 +46 @@
     """
     def __init__(self,
-                 scan_str=r'FinneganScanNumber%3a%20(\d+)',
+                 scan_str=r'FinneganScanNumber%3a%20(\d+)%20',
                  rawfn_str=r'RawFile%3a%20(.+raw)',
                  decoy_str=r'^IPI:REV_:IPI',
                  contaminant_str=r'^IPI:CON_:IPI'
                  ):
-        scan_regex = re.compile(scan_str)
+        self.scan_regex = re.compile(scan_str)
         decoy_regex = re.compile(decoy_str)
+        contaminant_regex = re.compile(contaminant_str)
         # Contaminants are not exactly decoy psms
-        self.non_target_regexes = (scan_regex, decoy_regex)
+        self.non_target_regexes = (contaminant_regex, decoy_regex)
         self.rawfn_regex = re.compile(rawfn_str)
-        self.contaminant_regex = re.compile(contaminant_str)
 
     def _parse_spectra_fn(self, dat_file):
@@ -95 +95 @@
                 charge = int(r_charge.rstrip('+'))
                 summspec.append((mz, charge))
-        return summspec
+            elif line.strip() == SEPARATOR:
+                return summspec
 
     def _parse_psms(self, dat_file):
@@ -133 +134 @@
                 return nativeid_psms
 
-    def _parse_spectra(self, dat_file):
+    def _parse_extraspec(self, dat_file):
         """Gets the data coming from the input file from Mascot dat
            format
         """
-        nativeid_spectra = defaultdict(dict)
-        nativeid = 1
-        for line in dat_file:
-            nativeid_str = ''.join(("query", str(nativeid)))
-            query_line = SECTION_TEMPLATE.substitute(section=nativeid_str)
-            if line.strip() == query_line:
-                current_id_mgf = nativeid_spectra[nativeid]
-                nativeid += 1
-            elif line.startswith("title="):
+        extraspec = list()
+        for line in dat_file:
+            if line.startswith("title="):
                 line = line.strip()
                 try:
                     quoted_rawfn = re.search(self.rawfn_regex, line).group(1)
+                    rawfn = urllib.unquote(quoted_rawfn)
                 except AttributeError:
-                    sys.exit("It seems there is no raw: field in TITLE")
-                rawfn = urllib.unquote(quoted_rawfn)
-                current_id_mgf["RawFile"] = rawfn
-                if self.scans_in_title:
-                    try:
-                        scan = int(re.search(self.scan_regex, line).group(1))
-                    except AttributeError:
-                        sys.exit("Default scan regex for TITLE field"
-                                 " doesn't match anything")
-                    current_id_mgf['Scan'] = scan
-            elif line.startswith("charge="):
-                charge = line.strip().split('=')[1]
-                current_id_mgf['Charge'] = charge
-            elif not self.scans_in_title and line.startswith("scans="):
-                scan = int(line.strip().split('=')[2])
-                current_id_mgf['Scan'] = scan
-        return nativeid_spectra
+                    sys.exit("It seems the raw regex is not valid")
+                try:
+                    scan = int(re.search(self.scan_regex, line).group(1))
+                except AttributeError:
+                    sys.exit("Default scan regex for TITLE field"
+                             " doesn't match anything")
+                extraspec.append((rawfn, scan))
+        return extraspec
 
     def parse(self, dat_file):
@@ -175 +162 @@
         summspec = self._parse_summary(dat_file)
         nativeid_psms = self._parse_psms(dat_file)
-        extraspec = self._parse_spectra(dat_file)
-        for native_id, psms in nativeid_psms.items():
-            for psm in psms:
-                psm['#SpectraFile'] = pkl_fn
-                psm['FragMode'] = frag_mode
-                psm.update(nativeid_spectra[native_id])
-                yield psm
+        extraspec = self._parse_extraspec(dat_file)
+        #for native_id, psms in nativeid_psms.items():
+        #    for psm in psms:
+        #        psm['#SpectraFile'] = pkl_fn
+        #        psm['FragMode'] = frag_mode
+        #        psm.update(nativeid_spectra[native_id])
+        #        yield psm
+        pass
 
 def get_prot_ids(accs):