Fixes #26: Ranges are [inclusive, exclusive)

Because of how the interval checking are defined, genomic ranges cannot start and end at the same spot. This is to keep the API consistent with the Python language.

For example:

```python
>>> a = 'abc'
>>> print(a[1:1])
''
```

bamnostic/bai.py

@@ -397,8 +397,6 @@ def query(self, ref_id, start, stop=-1):
             self.current_ref = self.get_ref(ref_id)
 
         # get linear index first
-        # how many windows do we need to go over
-        # because of floor div, we need to make it 0-based
 
         reg_lin_idx = start >> self.BAM_LIDX_SHIFT
 
@@ -412,9 +410,7 @@ def query(self, ref_id, start, stop=-1):
                 continue
 
             for chunk in bin_chunks:
-                if not chunk.voffset_beg <= linear_offset <= chunk.voffset_end:
-                    continue
-                else:
+                if chunk.voffset_beg <= linear_offset <= chunk.voffset_end:
                     return chunk.voffset_beg
 
     def seek(self, offset=None, whence=0):

bamnostic/bam.py

@@ -238,11 +238,11 @@ def __init__(self, filepath_or_object, mode="rb", max_cache=128, index_filename=
                     'duplicate_filehandle': locals()['duplicate_filehandle']}
         super(BamReader, self).__init__(**super_args)
 
-        self._igore_truncation = ignore_truncation
+        self._ignore_truncation = ignore_truncation
         self._truncated = self._check_truncation()
 
         # Check BAM file integrity
-        if not self._igore_truncation:
+        if not self._ignore_truncation:
             if self._truncated:
                 raise Exception('BAM file may be truncated. Turn off ignore_truncation if you wish to continue')
 
@@ -486,7 +486,7 @@ def has_index(self):
     def fetch(self, contig=None, start=None, stop=None, region=None,
               tid=None, until_eof=False, multiple_iterators=False,
               reference=None, end=None):
-        r"""Creates a generator that returns all reads within the given region
+        r"""Creates a generator that returns all reads within the given region. (inclusive, exclusive)
 
         Args:
             contig (str): name of reference/contig
@@ -539,6 +539,11 @@ def fetch(self, contig=None, start=None, stop=None, region=None,
             AssertionError: Malformed region: start should be <= stop, you entered 100, 10
 
         """
+        # Inclusive, exclusive. This means if start and stop are
+        # the same, then the user is *essentially* looking at nothing
+        # e.g. a = "abc"; print(a[1:1]) -> ''
+        if start == stop:
+            return
 
         if not self._random_access:
             raise ValueError('Random access not available due to lack of index file')
@@ -580,27 +585,40 @@ def fetch(self, contig=None, start=None, stop=None, region=None,
         # move to that virtual offset...should load the block into the cache
         # if it hasn't been visited before
         self.seek(first_read_block)
-        boundary_check = True
-        while boundary_check:
-            next_read = next(self)
+
+        for next_read in self:
             if not until_eof:
                 # check to see if the read is out of bounds of the region
-                if next_read.reference_name != query.contig:
-                    boundary_check = False
-                elif query.start < query.stop <= next_read.pos:
-                    boundary_check = False
-                elif next_read.pos <= query.start <= next_read.pos + len(next_read.seq):
-                    yield next_read
-                elif next_read.pos < query.start:
-                    continue
-                elif not query.start <= next_read.pos < query.stop:
+                # On the wrong contig -> not the right place
+                if next_read.reference_name != query.contig: 
+                    return None
+
+                # Read is too far left -> keep going
+                elif (next_read.pos + len(next_read.seq)) < query.start:
                     continue
+
+                # Originates outside, but overlaps
+                elif next_read.pos < query.start <= (next_read.pos + len(next_read)):
+                    yield next_read
+
+                # Read wholly inside region
+                elif query.start <= next_read.pos < query.stop:
+                    yield next_read
+
+                # Read too far right -> gotta stop
+                elif query.stop <= next_read.pos:
+                    return None
+
                 # check for stop iteration
                 elif next_read:
                     yield next_read
+
+                # Empty read
                 else:
-                    return
-            else:
+                    return None
+
+            # Read until the end of file
+            else: 
                 try:
                     yield next_read
                 except:
@@ -1030,7 +1048,7 @@ def next(self):
 
         read = bamnostic.AlignedSegment(self)
         if not read:
-            raise StopIteration
+            return
         return read
 
     def seekable(self):

bamnostic/bgzf.py

@@ -381,8 +381,7 @@ def seek(self, virtual_offset):
             assert start_offset == self._block_start_offset
         if within_block > len(self._buffer):
             if not (within_block == 0 and len(self._buffer) == 0):
-                raise ValueError("Within offset %i but block size only %i"
-                                 % (within_block, len(self._buffer)))
+                raise ValueError("Within offset {} but block size only {}".format(within_block, len(self._buffer)))
         self._within_block_offset = within_block
         return virtual_offset
 
@@ -431,7 +430,9 @@ def read(self, size=-1):
             # if there is still more to read
             elif size:
                 # pull rest of data from next block
-                return data + self.read(size)
+                data += self._buffer[self._within_block_offset: self._within_block_offset + size]
+                self._within_block_offset += size
+                return data
 
             else:
                 # Only needed the end of the last block

bamnostic/core.py

@@ -191,10 +191,10 @@ def __init__(self, _io):
             block_size = unpack_int32(bsize_buffer)[0]
 
         # Check for EOF: If the cursor is at the end of file, read() will return 
-        # an empty byte string. If 
+        # an empty byte string.
         except struct.error:
             if all([not bsize_buffer, not self._io._handle.read()]):
-                if not self._io._igore_truncation and not self._io._truncated:
+                if not self._io._ignore_truncation and not self._io._truncated:
                     raise StopIteration('End of file reached')
                 else:
                     raise StopIteration('Potential end of file reached')

codemeta.json

@@ -37,8 +37,8 @@
   "description": "BAMnostic is a Pure Python OS, version, and runtime agnostic BAM file parser",
   "keywords": "BAM, pysam, genomics, genetics, htslib, samtools",
   "license": "https://github.com/betteridiot/bamnostic/blob/master/LICENSE",
-  "softwareVersion": "v1.0.1,
-  "version": "v1.0.1",
+  "softwareVersion": "v1.0.2,
+  "version": "v1.0.2",
   "readme": "https://github.com/betteridiot/bamnostic/blob/master/README.md",
   "buildInstructions": "https://github.com/betteridiot/bamnostic/blob/master/README.md",
   "issueTracker": "https://github.com/betteridiot/bamnostic/issues",

docs/build/html/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 7fe887b2cbc5b91bf05ea54ef36c1a08
+config: 3ccb95d73a1a33548bd2a0dda7fa8824
 tags: 645f666f9bcd5a90fca523b33c5a78b7

docs/build/html/_modules/bamnostic/bai.html

@@ -8,7 +8,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>bamnostic.bai &mdash; bamnostic 1.0.1 documentation</title>
+  <title>bamnostic.bai &mdash; bamnostic 1.0.2 documentation</title>
 
 
 
@@ -56,7 +56,7 @@
 
 
               <div class="version">
-                1.0.1
+                1.0.2
               </div>
 
 
@@ -548,8 +548,6 @@ <h1>Source code for bamnostic.bai</h1><div class="highlight"><pre>
             <span class="bp">self</span><span class="o">.</span><span class="n">current_ref</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_ref</span><span class="p">(</span><span class="n">ref_id</span><span class="p">)</span>
 
         <span class="c1"># get linear index first</span>
-        <span class="c1"># how many windows do we need to go over</span>
-        <span class="c1"># because of floor div, we need to make it 0-based</span>
 
         <span class="n">reg_lin_idx</span> <span class="o">=</span> <span class="n">start</span> <span class="o">&gt;&gt;</span> <span class="bp">self</span><span class="o">.</span><span class="n">BAM_LIDX_SHIFT</span>
 
@@ -563,9 +561,7 @@ <h1>Source code for bamnostic.bai</h1><div class="highlight"><pre>
                 <span class="k">continue</span>
 
             <span class="k">for</span> <span class="n">chunk</span> <span class="ow">in</span> <span class="n">bin_chunks</span><span class="p">:</span>
-                <span class="k">if</span> <span class="ow">not</span> <span class="n">chunk</span><span class="o">.</span><span class="n">voffset_beg</span> <span class="o">&lt;=</span> <span class="n">linear_offset</span> <span class="o">&lt;=</span> <span class="n">chunk</span><span class="o">.</span><span class="n">voffset_end</span><span class="p">:</span>
-                    <span class="k">continue</span>
-                <span class="k">else</span><span class="p">:</span>
+                <span class="k">if</span> <span class="n">chunk</span><span class="o">.</span><span class="n">voffset_beg</span> <span class="o">&lt;=</span> <span class="n">linear_offset</span> <span class="o">&lt;=</span> <span class="n">chunk</span><span class="o">.</span><span class="n">voffset_end</span><span class="p">:</span>
                     <span class="k">return</span> <span class="n">chunk</span><span class="o">.</span><span class="n">voffset_beg</span></div>
 
 <div class="viewcode-block" id="Bai.seek"><a class="viewcode-back" href="../../bamnostic.html#bamnostic.bai.Bai.seek">[docs]</a>    <span class="k">def</span> <span class="nf">seek</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">offset</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">whence</span><span class="o">=</span><span class="mi">0</span><span class="p">):</span>

docs/build/html/_modules/bamnostic/bgzf.html

@@ -8,7 +8,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>bamnostic.bgzf &mdash; bamnostic 1.0.1 documentation</title>
+  <title>bamnostic.bgzf &mdash; bamnostic 1.0.2 documentation</title>
 
 
 
@@ -56,7 +56,7 @@
 
 
               <div class="version">
-                1.0.1
+                1.0.2
               </div>
 
 
@@ -532,8 +532,7 @@ <h1>Source code for bamnostic.bgzf</h1><div class="highlight"><pre>
             <span class="k">assert</span> <span class="n">start_offset</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_block_start_offset</span>
         <span class="k">if</span> <span class="n">within_block</span> <span class="o">&gt;</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="p">):</span>
             <span class="k">if</span> <span class="ow">not</span> <span class="p">(</span><span class="n">within_block</span> <span class="o">==</span> <span class="mi">0</span> <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">):</span>
-                <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Within offset </span><span class="si">%i</span><span class="s2"> but block size only </span><span class="si">%i</span><span class="s2">&quot;</span>
-                                 <span class="o">%</span> <span class="p">(</span><span class="n">within_block</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="p">)))</span>
+                <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Within offset </span><span class="si">{}</span><span class="s2"> but block size only </span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">within_block</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="p">)))</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">_within_block_offset</span> <span class="o">=</span> <span class="n">within_block</span>
         <span class="k">return</span> <span class="n">virtual_offset</span></div>
 
@@ -582,7 +581,9 @@ <h1>Source code for bamnostic.bgzf</h1><div class="highlight"><pre>
             <span class="c1"># if there is still more to read</span>
             <span class="k">elif</span> <span class="n">size</span><span class="p">:</span>
                 <span class="c1"># pull rest of data from next block</span>
-                <span class="k">return</span> <span class="n">data</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">size</span><span class="p">)</span>
+                <span class="n">data</span> <span class="o">+=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">_within_block_offset</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_within_block_offset</span> <span class="o">+</span> <span class="n">size</span><span class="p">]</span>
+                <span class="bp">self</span><span class="o">.</span><span class="n">_within_block_offset</span> <span class="o">+=</span> <span class="n">size</span>
+                <span class="k">return</span> <span class="n">data</span>
 
             <span class="k">else</span><span class="p">:</span>
                 <span class="c1"># Only needed the end of the last block</span>

docs/build/html/_modules/bamnostic/core.html

@@ -8,7 +8,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>bamnostic.core &mdash; bamnostic 1.0.1 documentation</title>
+  <title>bamnostic.core &mdash; bamnostic 1.0.2 documentation</title>
 
 
 
@@ -56,7 +56,7 @@
 
 
               <div class="version">
-                1.0.1
+                1.0.2
               </div>
 
 
@@ -342,10 +342,10 @@ <h1>Source code for bamnostic.core</h1><div class="highlight"><pre>
             <span class="n">block_size</span> <span class="o">=</span> <span class="n">unpack_int32</span><span class="p">(</span><span class="n">bsize_buffer</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
 
         <span class="c1"># Check for EOF: If the cursor is at the end of file, read() will return </span>
-        <span class="c1"># an empty byte string. If </span>
+        <span class="c1"># an empty byte string.</span>
         <span class="k">except</span> <span class="n">struct</span><span class="o">.</span><span class="n">error</span><span class="p">:</span>
             <span class="k">if</span> <span class="nb">all</span><span class="p">([</span><span class="ow">not</span> <span class="n">bsize_buffer</span><span class="p">,</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_io</span><span class="o">.</span><span class="n">_handle</span><span class="o">.</span><span class="n">read</span><span class="p">()]):</span>
-                <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_io</span><span class="o">.</span><span class="n">_igore_truncation</span> <span class="ow">and</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_io</span><span class="o">.</span><span class="n">_truncated</span><span class="p">:</span>
+                <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_io</span><span class="o">.</span><span class="n">_ignore_truncation</span> <span class="ow">and</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_io</span><span class="o">.</span><span class="n">_truncated</span><span class="p">:</span>
                     <span class="k">raise</span> <span class="ne">StopIteration</span><span class="p">(</span><span class="s1">&#39;End of file reached&#39;</span><span class="p">)</span>
                 <span class="k">else</span><span class="p">:</span>
                     <span class="k">raise</span> <span class="ne">StopIteration</span><span class="p">(</span><span class="s1">&#39;Potential end of file reached&#39;</span><span class="p">)</span>

docs/build/html/_modules/bamnostic/utils.html

@@ -8,7 +8,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>bamnostic.utils &mdash; bamnostic 1.0.1 documentation</title>
+  <title>bamnostic.utils &mdash; bamnostic 1.0.2 documentation</title>
 
 
 
@@ -56,7 +56,7 @@
 
 
               <div class="version">
-                1.0.1
+                1.0.2
               </div>
 
 

docs/build/html/_modules/index.html

@@ -8,7 +8,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>Overview: module code &mdash; bamnostic 1.0.1 documentation</title>
+  <title>Overview: module code &mdash; bamnostic 1.0.2 documentation</title>
 
 
 
@@ -56,7 +56,7 @@
 
 
               <div class="version">
-                1.0.1
+                1.0.2
               </div>
 
 

docs/build/html/_static/documentation_options.js

@@ -1,6 +1,6 @@
 var DOCUMENTATION_OPTIONS = {
     URL_ROOT: document.getElementById("documentation_options").getAttribute('data-url_root'),
-    VERSION: '1.0.1',
+    VERSION: '1.0.2',
     LANGUAGE: 'en',
     COLLAPSE_INDEX: false,
     FILE_SUFFIX: '.html',

docs/build/html/bamnostic.html

@@ -8,7 +8,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>bamnostic package &mdash; bamnostic 1.0.1 documentation</title>
+  <title>bamnostic package &mdash; bamnostic 1.0.2 documentation</title>
 
 
 
@@ -58,7 +58,7 @@
 
 
               <div class="version">
-                1.0.1
+                1.0.2
               </div>
 
 

docs/build/html/genindex.html

@@ -9,7 +9,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>Index &mdash; bamnostic 1.0.1 documentation</title>
+  <title>Index &mdash; bamnostic 1.0.2 documentation</title>
 
 
 
@@ -57,7 +57,7 @@
 
 
               <div class="version">
-                1.0.1
+                1.0.2
               </div>
 
 

docs/build/html/index.html

@@ -8,7 +8,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>Welcome to bamnostic’s documentation! &mdash; bamnostic 1.0.1 documentation</title>
+  <title>Welcome to bamnostic’s documentation! &mdash; bamnostic 1.0.2 documentation</title>
 
 
 
@@ -57,7 +57,7 @@
 
 
               <div class="version">
-                1.0.1
+                1.0.2
               </div>
 
 

docs/build/html/install.html

@@ -8,7 +8,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>Installation &mdash; bamnostic 1.0.1 documentation</title>
+  <title>Installation &mdash; bamnostic 1.0.2 documentation</title>
 
 
 
@@ -58,7 +58,7 @@
 
 
               <div class="version">
-                1.0.1
+                1.0.2
               </div>