.github/PULL_REQUEST_TEMPLATE.md

 This pull request addresses issue #...
 
-I hereby agree to dual licence this and any previous contributions under both
+<!--- Please read each of the following items and confirm by replacing
+ !--the [ ] with a [X] --->
+
+- [ ] I hereby agree to dual licence this and any previous contributions under both
 the _Biopython License Agreement_ **AND** the _BSD 3-Clause License_.
 
-I have read the ``CONTRIBUTING.rst`` file and understand that AppVeyor and
+- [ ] I have read the ``CONTRIBUTING.rst`` file and understand that AppVeyor and
 TravisCI will be used to confirm the Biopython unit tests and ``flake8`` style
 checks pass with these changes.
 
-I have added my name to the alphabetical contributors listings in the files
+- [ ] I have added my name to the alphabetical contributors listings in the files
 ``NEWS.rst`` and ``CONTRIB.rst`` as part of this pull request, am listed
 already, or do not wish to be listed. (*This acknowledgement is optional.*)

.gitignore

@@ -53,10 +53,12 @@ Tests/biosql.ini
 #TODO - The unit tests shouldn't leave temp files after running:
 Tests/BioSQL/temp_sqlite.db
 Tests/BioSQL/temp_sqlite.db-journal
+Tests/Cluster/cyano_result*
 
 #TODO - The Tutorial doctests should leave example files after
 #running Tests/test_Tutorial.py
 Doc/examples/other_trees.nwk
+Doc/examples/tree1.nwk
 
 #Ignore LaTeX temp files, and compiled output
 Doc/*.aux

.travis-tox.ini

@@ -33,6 +33,7 @@ envlist =
     style
     sdist
     bdist_wheel
+    api
     {py27,py34,py35,py36,pypy,pypy3}-cover
     {py27,py34,py35,py36,pypy,pypy3}-nocov
 
@@ -46,6 +47,7 @@ passenv =
     TRAVIS_*
     TOXENV
     CODECOV_*
+    HOME_4_TCOFFEE
 whitelist_externals =
     bash
     echo
@@ -57,18 +59,18 @@ deps =
     #Leaving py34 without any soft dependencies (just numpy)
     cover: coverage
     cover: codecov
-    {py27}: unittest2
-    {py27}: mysql-python
-    {py27,py36}: mmtf-python
-    {py27,py35}: reportlab
-    {py27,py34,py35,py36}: psycopg2-binary
-    {py27,py34,py35,py35}: mysql-connector-python-rf
-    {py27,py35,pypy}: rdflib
-    {pypy,pypy3}: numpy==1.12.1
-    {py27,py34,py36}: numpy
-    {py36}: scipy
-    {py27}: networkx
-    {py36}: matplotlib
+    py27: unittest2
+    py27: mysql-python
+    py27,py36: mmtf-python
+    py27,py35: reportlab
+    py27,py34,py35,py36: psycopg2-binary
+    py27,py34,py35,py35: mysql-connector-python-rf
+    py27,py35,pypy: rdflib
+    pypy,pypy3: numpy==1.12.1
+    py27,py34,py36: numpy
+    py36: scipy
+    py27: networkx
+    py36: matplotlib
 commands =
     #The bash call is a work around for special characters
     #The /dev/null is to hide the verbose output but leave warnings
@@ -85,6 +87,7 @@ commands =
 skip_install = True
 whitelist_externals =
     flake8
+    doc8
     rst-lint
     bash
 deps =
@@ -92,7 +95,9 @@ deps =
     flake8-docstrings
     flake8-blind-except
     flake8-rst-docstrings
+    py34,py35,py36: flake8-bugbear
     restructuredtext_lint
+    doc8
 commands =
     flake8 --max-line-length 82 setup.py
     # These folders each have their own .flake8 file:
@@ -108,6 +113,8 @@ commands =
     bash -c \'grep "^- " CONTRIB.rst | LC_ALL=C sort -u -c -f\'
     # Check copyright date
     bash -c \'grep "1999-`date +'%Y'`" LICENSE.rst\'
+    # Would like to tell doc8 to just check *.rst but does *.txt too:
+    bash -c "doc8 --ignore-path 'Doc/examples/ec_*.txt' *.rst Doc/"
     # Check no __docformat__ lines
     bash -c "if grep --include '*.py' -rn '^__docformat__ ' Bio BioSQL Tests Scripts Doc ; then echo 'Remove __docformat__ line(s), we assume restructuredtext.'; false; fi"
     # Check DOI link style, see https://www.crossref.org/display-guidelines/
@@ -129,3 +136,24 @@ deps =
     numpy
 commands =
     python setup.py bdist_wheel
+
+[testenv:api]
+# Note Sphinx likes to have the code installed so can import it
+skip_install = False
+whitelist_externals =
+    bash
+    sphinx-apidoc
+    make
+deps =
+    mmtf-python
+    mysql-connector-python-rf
+    numpy
+    rdflib
+    reportlab
+    scipy
+    sphinx>=1.8.0
+    numpydoc
+commands =
+    bash -c \'python setup.py install > /dev/null\'
+    bash -c \'mkdir -p Doc/api/_templates Doc/api/_static Doc/api/_build\'
+    make -C Doc/api/ html

.travis.yml

@@ -38,6 +38,13 @@ matrix:
         apt:
           packages:
       before_install: echo "Going to run basic checks"
+    - stage: test
+      python: 2.7
+      env: TOXENV=api
+      addons:
+        apt:
+          packages:
+      before_install: echo "Going to build API docs"
     - stage: test
       python: 2.7
       env: TOXENV=py27-cover
@@ -72,6 +79,8 @@ addons:
     - probcons
     - samtools
     - wise
+    - t-coffee
+    - ncbi-blast+
 
 # We setup $HOME/bin and add it to the $PATH for extra binaries we're using.
 #
@@ -99,6 +108,9 @@ before_install:
   - curl -L -O https://anaconda.org/bioconda/genepop/4.5.1/download/linux-64/genepop-4.5.1-0.tar.bz2
   # This will create ./bin/Genepop and a harmless ./info/ folder.
   - tar -jxvf genepop-4.5.1-0.tar.bz2
+  # Setup environment for t-coffee
+  - mkdir -p $HOME/tcoffee_temp
+  - export HOME_4_TCOFFEE=$HOME/tcoffee_temp
   # There are TravisCI provided versions of PyPy and PyPy3, but currently too old.
   # We therefore deactivate that, and download and unzip portable PyPy binaries.
   - |
@@ -140,7 +152,7 @@ install:
   - tox -c .travis-tox.ini -e $TOXENV --notest
 
 script:
-  - travis_wait tox -c .travis-tox.ini -e $TOXENV
+  - travis_wait 30 tox -c .travis-tox.ini -e $TOXENV
 
 notifications:
   email: false

Bio/.flake8

@@ -5,11 +5,10 @@ ignore =
     # =======================
     # flake: E###, F###, W###
     # =======================
-    # pycodestyle v2.3.1 default ignore is E121,E123,E126,E226,E24,E704,W503
-    # flake8 v3.3.0 default ignore is      E121,E123,E126,E226,E24,E704,W503,W504
-    #
+    # pycodestyle v2.4.0 default ignore is E121,E123,E126,E226,E24,E704,W503,W504
+    # flake8 v3.6.0 default ignore is      E121,E123,E126,E226,E24,E704,W503,W504
     # These are ignored by default:
-    E122,E123,E126,W503,
+    E122,E123,E126,W503,W504,
     # These are not ignored by default:
     # E127	continuation line over-indented for visual indent
     # E128	continuation line under-indented for visual indent
@@ -18,7 +17,7 @@ ignore =
     # F401	module imported but unused
     # F841	local variable name is assigned to but never used
     # TODO: Fix some of these?
-    E127,E128,E501,E731,F401,F841,
+    E501,E731,F401,F841,
     # =====================================
     # pydocstyle: D1## - Missing Docstrings
     # =====================================
@@ -36,6 +35,12 @@ ignore =
     # D211	No blank lines allowed before class docstring
     # We ignore D203 deliberately in favour of passing D211,
     D203,
+    # ====================
+    # flake8-bugbear: B###
+    # ====================
+    # B007	Loop control variable not used within the loop body.
+    #           If this is intended, start the name with an underscore.
+    B007,
     # ================================================
     # flake8-commas: C#### (in case installed locally)
     # ================================================

Bio/Affy/CelFile.py

 # Copyright 2004 by Harry Zuzan. All rights reserved.
 # Copyright 2016 by Adam Kurkiewicz. All rights reserved.
-# This code is part of the Biopython distribution and governed by its
-# license.  Please see the LICENSE file that should have been included
-# as part of this package.
+# This file is part of the Biopython distribution and governed by your
+# choice of the "Biopython License Agreement" or the "BSD 3-Clause License".
+# Please see the LICENSE file that should have been included as part of this
+# package.
 
 """Reading information from Affymetrix CEL files version 3 and 4."""
 

Bio/Affy/__init__.py

-# This code is part of the Biopython distribution and governed by its
-# license.  Please see the LICENSE file that should have been included
-# as part of this package.
-#
+# This file is part of the Biopython distribution and governed by your
+# choice of the "Biopython License Agreement" or the "BSD 3-Clause License".
+# Please see the LICENSE file that should have been included as part of this
+# package.
 
 """Deal with Affymetrix related data such as cel files."""

Bio/Align/AlignInfo.py

@@ -278,7 +278,7 @@ class SummaryInfo(object):
 
     def _pair_replacement(self, seq1, seq2, weight1, weight2,
                           start_dict, ignore_chars):
-        """Compare two sequences and generate info on the replacements seen.
+        """Compare two sequences and generate info on the replacements seen (PRIVATE).
 
         Arguments:
          - seq1, seq2 - The two sequences to compare.
@@ -549,7 +549,7 @@ class SummaryInfo(object):
 
     def _get_letter_freqs(self, residue_num, all_records, letters, to_ignore,
                           pseudo_count=0, e_freq_table=None, random_expected=None):
-        """Determine the frequency of specific letters in the alignment.
+        """Determine the frequency of specific letters in the alignment (PRIVATE).
 
         Arguments:
          - residue_num - The number of the column we are getting frequencies
@@ -632,7 +632,7 @@ class SummaryInfo(object):
 
     def _get_column_info_content(self, obs_freq, e_freq_table, log_base,
                                  random_expected):
-        """Calculate the information content for a column.
+        """Calculate the information content for a column (PRIVATE).
 
         Arguments:
          - obs_freq - The frequencies observed for each letter in the column.

Bio/Align/Applications/_MSAProbs.py

@@ -44,8 +44,7 @@ class MSAProbsCommandline(AbstractCommandline):
     def __init__(self, cmd="msaprobs", **kwargs):
         """Initialize the class."""
         # order of parameters is the same as in msaprobs -help
-        self.parameters = \
-            [
+        self.parameters = [
             _Option(["-o", "--outfile", "outfile"],
                     "specify the output file name (STDOUT by default)",
                     filename=True,

Bio/Align/__init__.py

@@ -19,7 +19,14 @@ from Bio.Seq import Seq
 from Bio.SeqRecord import SeqRecord, _RestrictedDict
 from Bio import Alphabet
 
+try:
     from Bio.Align import _aligners
+except ImportError as e:
+    new_exc = ImportError("{}: you should not import directly from the "
+                          "biopython source directory; please exit the source "
+                          "tree and re-launch your code from there".format(e))
+    new_exc.__cause__ = None
+    raise new_exc
 
 
 class MultipleSeqAlignment(object):
@@ -149,28 +156,7 @@ class MultipleSeqAlignment(object):
         {'tool': 'demo'}
         >>> align.column_annotations
         {'stats': 'CCCXCCC'}
-
-        NOTE - The older Bio.Align.Generic.Alignment class only accepted a
-        single argument, an alphabet.  This is still supported via a backwards
-        compatible "hack" so as not to disrupt existing scripts and users, but
-        is deprecated and will be removed in a future release.
         """
-        if isinstance(records, (Alphabet.Alphabet, Alphabet.AlphabetEncoder)):
-            if alphabet is None:
-                # TODO - Remove this backwards compatible mode!
-                alphabet = records
-                records = []
-                import warnings
-                from Bio import BiopythonDeprecationWarning
-                warnings.warn("Invalid records argument: While the old "
-                              "Bio.Align.Generic.Alignment class only "
-                              "accepted a single argument (the alphabet), the "
-                              "newer Bio.Align.MultipleSeqAlignment class "
-                              "expects a list/iterator of SeqRecord objects "
-                              "(which can be an empty list) and an optional "
-                              "alphabet argument", BiopythonDeprecationWarning)
-            else:
-                raise ValueError("Invalid records argument")
         if alphabet is not None:
             if not isinstance(alphabet, (Alphabet.Alphabet, Alphabet.AlphabetEncoder)):
                 raise ValueError("Invalid alphabet argument")

Bio/AlignIO/FastaIO.py

@@ -51,10 +51,9 @@ def _extract_alignment_region(alignment_seq_with_flanking, annotation):
         end = int(annotation['al_stop']) - display_start + 1
     else:
         # FASTA has flipped this sequence...
-        start = display_start \
-              - int(annotation['al_start'])
-        end = display_start \
-              - int(annotation['al_stop']) + 1
+        start = display_start - int(annotation['al_start'])
+        end = display_start - int(annotation['al_stop']) + 1
+
     end += align_stripped.count("-")
     if start < 0 or start >= end or end > len(align_stripped):
         raise ValueError("Problem with sequence start/stop,\n%s[%i:%i]\n%s"

Bio/AlignIO/MauveIO.py

@@ -80,8 +80,8 @@ from .Interfaces import AlignmentIterator
 from .Interfaces import SequentialAlignmentWriter
 
 
-XMFA_HEADER_REGEX = re.compile("> (?P<id>\d+):(?P<start>\d+)-(?P<end>\d+) (?P<strand>[+-]) (?P<name>.*)")
-XMFA_HEADER_REGEX_BIOPYTHON = re.compile("> (?P<id>\d+):(?P<start>\d+)-(?P<end>\d+) (?P<strand>[+-]) (?P<name>[^#]*) # (?P<realname>.*)")
+XMFA_HEADER_REGEX = re.compile(r"> (?P<id>\d+):(?P<start>\d+)-(?P<end>\d+) (?P<strand>[+-]) (?P<name>.*)")
+XMFA_HEADER_REGEX_BIOPYTHON = re.compile(r"> (?P<id>\d+):(?P<start>\d+)-(?P<end>\d+) (?P<strand>[+-]) (?P<name>[^#]*) # (?P<realname>.*)")
 ID_LINE_FMT = "> {seq_name}:{start}-{end} {strand} {file} # {ugly_hack}\n"
 
 

Bio/AlignIO/PhylipIO.py

@@ -98,14 +98,7 @@ class PhylipWriter(SequentialAlignmentWriter):
             Note that Tab characters count as only one character in the
             species names. Their inclusion can cause trouble.
             """
-            name = record.id.strip()
-            # Either remove the banned characters, or map them to something
-            # else like an underscore "_" or pipe "|" character...
-            for char in "[](),":
-                name = name.replace(char, "")
-            for char in ":;":
-                name = name.replace(char, "|")
-            name = name[:id_width]
+            name = sanitize_name(record.id, id_width)
             if name in names:
                 raise ValueError("Repeated name %r (originally %r), "
                                  "possibly due to truncation"
@@ -329,14 +322,9 @@ class SequentialPhylipWriter(SequentialAlignmentWriter):
         # Apply this test *after* cleaning the identifiers
         names = []
         for record in alignment:
-            name = record.id.strip()
             # Either remove the banned characters, or map them to something
             # else like an underscore "_" or pipe "|" character...
-            for char in "[](),":
-                name = name.replace(char, "")
-            for char in ":;":
-                name = name.replace(char, "|")
-            name = name[:id_width]
+            name = sanitize_name(record.id, id_width)
             if name in names:
                 raise ValueError("Repeated name %r (originally %r), "
                                  "possibly due to truncation"
@@ -441,3 +429,19 @@ class SequentialPhylipIterator(PhylipIterator):
                              id=i, name=i, description=i)
                    for (i, s) in zip(ids, seqs))
         return MultipleSeqAlignment(records, self.alphabet)
+
+
+def sanitize_name(name, width=None):
+    """Sanitise sequence identifier for output.
+
+    Removes the banned characters "[]()" and replaces the characters ":;"
+    with "|". The name is truncated to "width" characters if specified.
+    """
+    name = name.strip()
+    for char in "[](),":
+        name = name.replace(char, "")
+    for char in ":;":
+        name = name.replace(char, "|")
+    if width is not None:
+        name = name[:width]
+    return name

Bio/Application/__init__.py

@@ -490,13 +490,12 @@ class AbstractCommandline(object):
         # Using universal newlines is important on Python 3, this
         # gives unicode handles rather than bytes handles.
 
-        # Windows 7, 8 and 8.1 want shell = True
-        # TODO: Test under Windows 10 and revisit platform detection.
+        # Windows 7, 8, 8.1 and 10 want shell = True
         if sys.platform != "win32":
             use_shell = True
         else:
             win_ver = platform.win32_ver()[0]
-            if win_ver in ["7", "8", "post2012Server"]:
+            if win_ver in ["7", "8", "post2012Server", "10"]:
                 use_shell = True
             else:
                 use_shell = False

Bio/Blast/Applications.py

@@ -19,6 +19,7 @@ Wrappers for the new NCBI BLAST+ tools (written in C++):
  - NcbirpstblastnCommandline - Translated Reverse Position Specific BLAST
  - NcbideltablastCommandline - Protein-Protein domain enhanced lookup time accelerated blast
  - NcbiblastformatterCommandline - Convert ASN.1 to other BLAST output formats
+ - NcbimakeblastdbCommandline - Application to create BLAST databases
 
 For further details, see:
 
@@ -1234,8 +1235,146 @@ class NcbideltablastCommandline(_Ncbiblast2SeqCommandline):
         _Ncbiblast2SeqCommandline.__init__(self, cmd, **kwargs)
 
 
+class NcbimakeblastdbCommandline(AbstractCommandline):
+    """Wrapper for the NCBI BLAST+ program makeblastdb.
+
+    This is a wrapper for the NCBI BLAST+ makeblastdb application
+    to create BLAST databases. By default, this creates a blast database
+    with the same name as the input file. The default output location
+    is the same directory as the input.
+
+    >>> from Bio.Blast.Applications import NcbimakeblastdbCommandline
+    >>> cline = NcbimakeblastdbCommandline(dbtype="prot",
+    ...                                    input_file="NC_005816.faa")
+    >>> cline
+    NcbimakeblastdbCommandline(cmd='makeblastdb', dbtype='prot', input_file='NC_005816.faa')
+    >>> print(cline)
+    makeblastdb -dbtype prot -in NC_005816.faa
+
+    You would typically run the command line with cline() or via the Python
+    subprocess module, as described in the Biopython tutorial.
+    """
+
+    def __init__(self, cmd="makeblastdb", **kwargs):
+        """Initialize the class."""
+        self.parameters = [
+            # Basic input options
+            _Switch(["-h", "h"],
+                    "Print USAGE and DESCRIPTION; ignore other arguments."),
+            _Switch(["-help", "help"],
+                    "Print USAGE, DESCRIPTION and ARGUMENTS description; "
+                    "ignore other arguments."),
+            _Switch(["-version", "version"],
+                    "Print version number;  ignore other arguments."),
+            # Output configuration options
+            _Option(["-out", "out"],
+                    "Output file for alignment.",
+                    filename=True,
+                    equate=False),
+            # makeblastdb specific options
+            _Option(["-dbtype", "dbtype"],
+                    "Molecule type of target db ('nucl' or 'prot')",
+                    equate=False,
+                    is_required=True,
+                    checker_function=lambda x: x == 'nucl' or x == 'prot'),
+            _Option(["-in", "input_file"],
+                    "Input file/database name",
+                    filename=True,
+                    equate=False),
+            _Option(["-input_type", "input_type"],
+                    "Type of the data specified in input_file. "
+                    "Default = 'fasta'. Added in BLAST 2.2.26.",
+                    filename=False,
+                    equate=False,
+                    checker_function=self._input_type_checker),
+            _Option(["-title", "title"],
+                    "Title for BLAST database",
+                    filename=False,
+                    equate=False),
+            _Switch(["-parse_seqids", "parse_seqids"],
+                    "Option to parse seqid for FASTA input if set, for all "
+                    "other input types seqids are parsed automatically"),
+            _Switch(["-hash_index", "hash_index"],
+                    "Create index of sequence hash values."),
+            _Option(["-mask_data", "mask_data"],
+                    "Comma-separated list of input files containing masking "
+                    "data as produced by NCBI masking applications "
+                    "(e.g. dustmasker, segmasker, windowmasker)",
+                    filename=True,
+                    equate=False),
+            _Option(["-mask_id", "mask_id"],
+                    "Comma-separated list of strings to uniquely identify the "
+                    "masking algorithm",
+                    filename=False,
+                    equate=False),
+            _Option(["-mask_desc", "mask_desc"],
+                    "Comma-separated list of free form strings to describe "
+                    "the masking algorithm details",
+                    filename=False,
+                    equate=False),
+            _Switch(["-gi_mask", "gi_mask"],
+                    "Create GI indexed masking data."),
+            _Option(["-gi_mask_name", "gi_mask_name"],
+                    "Comma-separated list of masking data output files.",
+                    filename=False,
+                    equate=False),
+            _Option(["-max_file_sz", "max_file_sz"],
+                    "Maximum file size for BLAST database files. "
+                    "Default = '1GB'",
+                    filename=False,
+                    equate=False),
+            _Option(["-logfile", "logfile"],
+                    "File to which the program log should be redirected",
+                    filename=True,
+                    equate=False),
+            _Option(["-taxid", "taxid"],
+                    "Taxonomy ID to assign to all sequences",
+                    filename=False,
+                    equate=False,
+                    checker_function=lambda x: type(x)(int(x)) == x),
+            _Option(["-taxid_map", "taxid_map"],
+                    "Text file mapping sequence IDs to taxonomy IDs. "
+                    "Format:<SequenceId> <TaxonomyId><newline>",
+                    filename=True,
+                    equate=False),
+        ]
+        AbstractCommandline.__init__(self, cmd, **kwargs)
+
+    def _input_type_checker(command, x):
+        return x in ('asn1_bin', 'asn1_txt', 'blastdb', 'fasta')
+
+    def _validate(self):
+        incompatibles = {"mask_id": ["gi_mask"],
+                         "gi_mask": ["mask_id"],
+                         "taxid": ["taxid_map"]}
+
+        # Copied from _NcbibaseblastCommandline class above.
+        # Code repeated here for python2 and 3 comptaibility,
+        # because this is not a _NcbibaseblastCommandline subclass.
+        for a in incompatibles:
+            if self._get_parameter(a):
+                for b in incompatibles[a]:
+                    if self._get_parameter(b):
+                        raise ValueError("Options %s and %s are incompatible."
+                                         % (a, b))
+
+        if self.mask_id and not self.mask_data:
+            raise ValueError("Option mask_id requires mask_data to be set.")
+        if self.mask_desc and not self.mask_id:
+            raise ValueError("Option mask_desc requires mask_id to be set.")
+        if self.gi_mask and not self.parse_seqids:
+            raise ValueError("Option gi_mask requires parse_seqids to be set.")
+        if self.gi_mask_name and not (self.mask_data and self.gi_mask):
+            raise ValueError("Option gi_mask_name requires mask_data and "
+                             "gi_mask to be set.")
+        if self.taxid_map and not self.parse_seqids:
+            raise ValueError("Option taxid_map requires parse_seqids "
+                             "to be set.")
+        AbstractCommandline._validate(self)
+
+
 def _test():
-    """Run the Bio.Blast.Applications module's doctests."""
+    """Run the Bio.Blast.Applications module's doctests (PRIVATE)."""
     import doctest
     doctest.testmod(verbose=1)
 

Bio/Blast/NCBIWWW.py

@@ -172,16 +172,16 @@ def qblast(program, database, sequence, url_base=NCBI_BLAST_URL,
     # will take longer thus at least 70s with delay. Therefore,
     # start with 20s delay, thereafter once a minute.
     delay = 20  # seconds
-    previous = time.time()
     while True:
         current = time.time()
-        wait = previous + delay - current
+        wait = qblast._previous + delay - current
         if wait > 0:
             time.sleep(wait)
-            previous = current + wait
+            qblast._previous = current + wait
         else:
-            previous = current
-        if delay < 60:
+            qblast._previous = current
+        # delay by at least 60 seconds only if running the request against the public NCBI API
+        if delay < 60 and url_base == NCBI_BLAST_URL:
             # Wasn't a quick return, must wait at least a minute
             delay = 60
 
@@ -203,10 +203,12 @@ def qblast(program, database, sequence, url_base=NCBI_BLAST_URL,
         status = results[i + len("Status="):j].strip()
         if status.upper() == "READY":
             break
-
     return StringIO(results)
 
 
+qblast._previous = 0
+
+
 def _parse_qblast_ref_page(handle):
     """Extract a tuple of RID, RTOE from the 'please wait' page (PRIVATE).
 

Bio/Blast/NCBIXML.py

@@ -37,10 +37,10 @@ class _XMLparser(ContentHandler):
         self._debug_ignore_list = []
 
     def _secure_name(self, name):
-        """Remove 'dangerous' from tag names.
+        """Remove 'dangerous' from tag names (PRIVATE).
 
         Arguments:
-         - name -- name to be 'secured'
+         - name -- name to be 'secured'.
 
         """
         # Replace '-' with '_' in XML tag names
@@ -160,10 +160,12 @@ class BlastParser(_XMLparser):
         self._parameters.filter = None  # Maybe I should update the class?
 
     def _start_Iteration(self):
+        """Start interaction (PRIVATE)."""
         self._blast = Record.Blast()
         pass
 
     def _end_Iteration(self):
+        """End interaction (PRIVATE)."""
         # We stored a lot of generic "top level" information
         # in self._header (an object of type Record.Header)
         self._blast.reference = self._header.reference
@@ -222,14 +224,14 @@ class BlastParser(_XMLparser):
 
     # Header
     def _end_BlastOutput_program(self):
-        """BLAST program, e.g., blastp, blastn, etc.
+        """BLAST program, e.g., blastp, blastn, etc. (PRIVATE).
 
         Save this to put on each blast record object
         """
         self._header.application = self._value.upper()
 
     def _end_BlastOutput_version(self):
-        """Version number and date of the BLAST engine.
+        """Version number and date of the BLAST engine (PRIVATE).
 
         e.g. "BLASTX 2.2.12 [Aug-07-2005]" but there can also be
         variants like "BLASTP 2.2.18+" without the date.
@@ -359,17 +361,18 @@ class BlastParser(_XMLparser):
         self._parameters.filter = self._value
 
     # def _end_Parameters_pattern(self):
-    #     """Pattern used for phi-blast search
+    #     """Pattern used for phi-blast search (PRIVATE).
     #     """
     #     pass # XXX TODO PSI
 
     # def _end_Parameters_entrez_query(self):
-    #     """Entrez query used to limit search
+    #     """Entrez query used to limit search (PRIVATE).
     #     """
     #     pass # XXX TODO PSI
 
     # Hits
     def _start_Hit(self):
+        """Start filling records (PRIVATE)."""
         self._blast.alignments.append(Record.Alignment())
         self._blast.descriptions.append(Record.Description())
         self._blast.multiple_alignment = []
@@ -378,6 +381,7 @@ class BlastParser(_XMLparser):
         self._descr.num_alignments = 0
 
     def _end_Hit(self):
+        """Clear variables (PRIVATE)."""
         # Cleanup
         self._blast.multiple_alignment = None
         self._hit = None