Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Speed RagTag up a few orders of magnitude on fragmented assemblies with caching #178

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Speed RagTag up a few orders of magnitude on fragmented assemblies with caching #178

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 14 additions & 2 deletions ragtag_utilities/AGPFile.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,6 +73,8 @@ def __init__(self, in_file, mode="r"):
self._comment_lines = []
self._objects = []

self._n_lines = 0

# Store info enabling us to keep track of the state of the AGP file
self._current_obj = None
self._seen_objs = set()
Expand Down Expand Up @@ -106,6 +108,7 @@ def _read_file(self):
if line.startswith("#"):
if not in_body:
self._comment_lines.append(line)
self._n_lines += 1
else:
raise AGPError(self.fname, line_number, "illegal comment in AGP body")
continue
Expand Down Expand Up @@ -141,13 +144,15 @@ def _add_line(self, agp_line):
# Add the new object to our master list
agp_obj = AGPObject(self.fname, agp_line)
self._objects.append(agp_obj)
self._n_lines += agp_obj.num_lines

# Initialize all the info for this new object
self._current_obj = agp_obj.obj
self._seen_objs.add(agp_obj.obj)

else:
self._objects[-1].add_line(agp_line)
self._n_lines += 1

@property
def agp_version(self):
Expand All @@ -160,7 +165,7 @@ def fname(self):
@property
def num_lines(self):
""" Calculate the number of lines in the current state of the AGP file. """
return sum([len(self._comment_lines)] + [obj.num_lines for obj in self._objects])
return self._n_lines

@property
def num_objs(self):
Expand All @@ -169,13 +174,15 @@ def num_objs(self):
def add_pragma(self):
pragma = "## agp-version {}".format(self.agp_version)
if self._comment_lines:
self._n_lines -= len(self._comment_lines)
new_comment_lines = [pragma]
for i in self._comment_lines:
if i != pragma:
new_comment_lines.append(i)
self._comment_lines = new_comment_lines
else:
self._comment_lines.append(pragma)
self._n_lines += len(self._comment_lines)

def iterate_objs(self):
""" Iterate over the objects of the AGP file. """
Expand All @@ -197,6 +204,7 @@ def add_comment(self, c):

if c not in self._comment_lines:
self._comment_lines.append(c)
self._n_lines += 1

def add_seq_line(self, obj, obj_beg, obj_end, pid, comp_type, comp, comp_beg, comp_end, orientation):
"""
Expand Down Expand Up @@ -244,6 +252,8 @@ def pop_agp_line(self):
else:
self._objects[-1].pop_line()

self._n_lines -= 1

def write(self):
""" Write the agp contents to a file. """
with open(self.fname, "w") as f:
Expand All @@ -269,6 +279,7 @@ def __init__(self, agp_fname, in_agp_line):
self.fname = agp_fname
self._obj = in_agp_line.obj
self._agp_lines = []
self._n_agp_lines = 0

# Store info enabling us to keep track of the state of the object
self.previous_pid = 0
Expand Down Expand Up @@ -300,7 +311,7 @@ def obj_len(self):

@property
def num_lines(self):
return len(self._agp_lines)
return self._n_agp_lines

def add_line(self, agp_line):
# Perform validity checks if this is a new object
Expand All @@ -319,6 +330,7 @@ def add_line(self, agp_line):
self.previous_pid = agp_line.pid
self.obj_intervals.append((agp_line.obj_beg - 1, agp_line.obj_end))
self._agp_lines.append(agp_line)
self._n_agp_lines += 1

def iterate_lines(self):
for i in self._agp_lines:
Expand Down