Changeset 25

Timestamp:

Aug 11, 2010, 4:04:36 PM (10 years ago)

Author:

j@…

bzr:base-revision:

j@dannynavarro.net-20100806093012-l67phkga1smqy5lj

bzr:committer:

Danny Navarro <j@dannynavarro.net>

bzr:file-ids:

.bzrignore bzrignore-20100730084509-1oxl7srf8gii89tg-1
mzcms/models.py models.py-20100730084238-fjjwldiefr0w07zv-4
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-20100806113756-c05d2haeot4rmaiy

bzr:revno:

25

bzr:revprop:branch-nick:

trunk

bzr:root:

trunk

bzr:timestamp:

2010-08-06 13:37:56.970999956 +0200

bzr:user-agent:

bzr2.1.2+bzr-svn1.0.3

svn:original-date:

2010-08-06T11:37:56.971000Z

Message:

Pseudocode for parse_dats

Location:

trunk

Files:

• .bzrignore (modified) (1 diff)
• mzcms/models.py (modified) (2 diffs)
• mzcms/parsers.py (modified) (4 diffs)

trunk/.bzrignore

@@ -2 +2 @@
 *.egg-info
 tags
+.coverage

trunk/mzcms/models.py

@@ -9 +9 @@
 class Experiment(Folder):
     __parent__ = __name__ = None
-    def __init__(self, proteins, peptides, spectra, psms):
+    def __init__(self, subfolders):
         super(Experiment, self).__init__()
-        self['proteins'] = Proteins(proteins)
-        self['peptides'] = Peptides(peptides)
-        self['spectra'] = Spectra(spectra)
-        self['psms'] = Psms(psms)
+        for subfolder in subfolders:
+            self[subfolder.name] = subfolder
 
 class Proteins(Folder):
@@ -74 +72 @@
 def appmaker(zodb_root):
     if not 'app_root' in zodb_root:
-        data = parse_dats('./dats')
-        app_root = Experiment(data)
+        folders = parse_dats('./dats', proteins_factory=Proteins,
+                             peptides_factory=Peptides,
+                             spectra_factory=Spectra,
+                             psms_factory=Psms,
+                             )
+        app_root = Experiment(folders)
         zodb_root['app_root'] = app_root
         import transaction

trunk/mzcms/parsers.py

@@ -31 +31 @@
 RAWFN_REGEX = re.compile(r'raw%3a%20(.+raw)')
 
-class MascotParser(object):
-    """Mascot Parser
-    """
-
+class DatParser(object):
+    """Mascot Dat Parser
+    """
     def __init__(self, decoy_str, scans_in_title=False):
         self.decoy_regex = re.compile(decoy_str)
@@ -47 +46 @@
             if line.startswith("FILE="):
                 #XXX: There must be something in the standard library
-                # to normalize paths
+                # to normalize this properly
                 full_path = line.strip().split('=')[1]
                 norm_path = full_path.replace("\\", "/")
@@ -187 +186 @@
         writer.writerow(psm)
 
+def parse_dats(dats_dir, proteins_factory=dict, peptides_factory=dict,
+               spectra_factory=dict, psms_factory=dict):
+    """Parses all the dat files in dats_dir
+    """
+    dats = get_dat_files(dats_dir)
+    proteins = proteins_factory()
+    peptides = peptides_factory()
+    spectra = spectra_factory()
+    psms = psms_factory()
+    dat_parser = DatParser(decoy_str, scans_in_title)
+    for dat in dats:
+        dat_proteins, dat_peptides, dat_spectra, dat_psms = dat_parser.parse(file)
+        proteins.update(dat_proteins)
+        peptides.update(dat_peptides)
+        spectra.update(dat_spectra)
+        psms.update(dat_psms)
+    return proteins, peptides, spectra, psms
+
 def main():
     usage = "usage: %prog [options] mascotresult1.dat [mascotresult2.dat ...]"
@@ -227 +244 @@
                 for arg in args:
                     with open(arg) as in_file:
-                        dat_parser = MascotParser(options.decoy_str,
+                        dat_parser = DatParser(options.decoy_str,
                                 scans_in_title = options.scans_in_title)
                         psms = dat_parser.parse(in_file)