def test_file_paths(self):
self.assertPathsEqual(expected_file_paths, file_paths(self.filtered_walk()))
self.assertPathsEqual(expected_file_paths[len(depth_0_file_paths):],
file_paths(self.filtered_walk(min_depth=1)))
self.assertPathsEqual(depth_0_file_paths, file_paths(self.filtered_walk(depth=0)))
walk_iter = self.filtered_walk(included_files=['file*'],
excluded_files=['*2*'],
included_dirs=['sub*'],
excluded_dirs=['*2'])
self.assertPathsEqual(filtered_file_paths, file_paths(walk_iter))
def test_file_paths(self):
self.assertPathsEqual(expected_file_paths, file_paths(self.filtered_walk()))
self.assertPathsEqual(expected_file_paths[len(depth_0_file_paths):],
file_paths(self.filtered_walk(min_depth=1)))
self.assertPathsEqual(depth_0_file_paths, file_paths(self.filtered_walk(depth=0)))
walk_iter = self.filtered_walk(included_files=['file*'],
excluded_files=['*2*'],
included_dirs=['sub*'],
excluded_dirs=['*2'])
self.assertPathsEqual(filtered_file_paths, file_paths(walk_iter))
def index_podcasts():
files = file_paths(
filtered_walk(
'static/podcasts',
included_files=['*.mp3'],
))
return files
def main(srcdir, destpath, img_size, thread_number):
#Iterate csv container
csvFiles = file_paths(
filtered_walk(srcdir, depth=1, included_files='*.csv'))
for csvfile in list(csvFiles):
#Download files
down(csvfile, destpath, img_size, thread_number)
def index_content(root_dir, file_types, content_type):
""" Scan the media directory, creating an index of file properties for display and serving
"""
logger.debug('indexing')
hasher = sha1()
content_dir = os.path.join(root_dir, app.config['CONTENT_DIR'])
files = file_paths(filtered_walk(
content_dir,
included_files=file_types,
))
for contentfile in files:
rel_path = os.path.relpath(contentfile, root_dir)
filepath = os.path.join(root_dir, rel_path)
filename = os.path.split(contentfile)[1]
local_path = os.path.relpath(filepath, root_dir)
if os.path.exists(os.path.join(filepath, 'folder.jpg')):
img = os.path.join(filepath, 'folder.jpg')
else:
img = ''
hasher.update(local_path)
file_key = hasher.hexdigest()
tags = _get_tags(filepath)
media = Media()
media.type = content_type
media.path = filepath
media.filename = filename
media.file_id = file_key
media.tags = tags
media.img = img
media.type = content_type
media.save()
def index_content(root_dir, file_types, content_type):
""" Scan the media directory, creating an index of file properties for display and serving
"""
logger.debug('indexing')
hasher = sha1()
content_dir = os.path.join(root_dir, app.config['CONTENT_DIR'])
files = file_paths(filtered_walk(content_dir, included_files=file_types, ))
for contentfile in files:
rel_path = os.path.relpath(contentfile, root_dir)
filepath = os.path.join(root_dir, rel_path)
filename = os.path.split(contentfile)[1]
local_path = os.path.relpath(filepath, root_dir)
if os.path.exists(os.path.join(filepath, 'folder.jpg')):
img = os.path.join(filepath, 'folder.jpg')
else:
img = ''
hasher.update(local_path)
file_key = hasher.hexdigest()
tags = _get_tags(filepath)
media = Media()
media.type = content_type
media.path = filepath
media.filename = filename
media.file_id = file_key
media.tags = tags
media.img = img
media.type = content_type
media.save()
def file(path: str, exts: list) -> list:
''' 在{path}中搜索所有扩展名符合{exts}的文件，并转换成绝对路径。
Args:
path: 文件或目录
exts: 扩展名列表
Returns:
list: 文件绝对路径列表
'''
# 将path转换为绝对路径
if not os.path.isabs(path):
abs_path = os.path.join(os.getcwd(), path)
else:
abs_path = path
# 遍历path，并返回指定扩展名的文件
if os.path.isfile(path) and os.path.splitext(path)[1].lower() in exts:
return [abs_path]
if os.path.isdir(abs_path):
return filter(
None,
list(
file_paths(
filtered_walk(abs_path,
included_files=['*' + e for e in exts]))))
return []
def directory_to_csv(dicom_path, csv_file_path, tags_in_files,
tags_to_exclude):
"""
directory_to_csv iterates over a directory, finds dicom files with
a .dcm extension and then creates a spreadsheet containing all of
the tag values for the tags in the csv for every dicom file
Args:
dicom_path (str): Path to scan for dicom files.
csv_file_path (str): Path and file name for the output csv file.
tags_in_files (dict): Dictionary containing tags to include in the csv
tags_to_exclude (dict): Dictionary containing tags to exclude in the csv
Returns:
None
"""
tags_in_files = tags_in_files.copy() # copy because we're going to modify
for tag_to_exclude in tags_to_exclude:
if tag_to_exclude in tags_in_files:
del tags_in_files[tag_to_exclude]
# sort by group and then element number
tags_in_files = OrderedDict(
sorted(tags_in_files.items(), key=(lambda k: (k[1][0], k[1][1]))))
dicom_file_paths = file_paths(
filtered_walk(dicom_path, included_files=["*.dcm"]))
with open(csv_file_path, "w") as f:
writer = csv.writer(f)
# write the headers
header_row = list(tags_in_files.keys())
header_row.append("FilePath")
writer.writerow(header_row)
# write the rows
for dicom_file_path in dicom_file_paths:
dicom_file = pydicom.read_file(dicom_file_path)
row_vals = []
for keyword in tags_in_files:
tag_val = dicom_file.get(keyword)
if tag_val is None:
tag_val = ""
else:
if isinstance(tag_val, Sequence) and not isinstance(
tag_val, (str, bytes, bytearray)):
tag_val = "^".join([str(x) for x in tag_val])
elif not isinstance(tag_val, str):
tag_val = str(tag_val)
tag_val = (tag_val.replace(",", "^").replace("\n",
"").replace(
"\r", ""))
row_vals.append(tag_val)
row_vals.append(dicom_file_path)
writer.writerow(row_vals)
def _display_files_not_restored(self, restore_to):
print
count = 0
files = file_paths(filtered_walk(restore_to))
for item in files:
count = count + 1
print('{}. {}'.format(count, item))
if count:
print(yellow(
"The {} files listed above were not restored "
"(just so you know).".format(count)
))
print
def sequence(self, formats):
'''return final list'''
total = []
print 'iQuence Searching Path: %s' % self.topdir
fileset = file_paths(filtered_walk(self.topdir, depth=self.depth ,included_files=formats))
#~ print files
#for i in fileset: print i
#~ for pattern in formats:
#~ fileset = self.find_files(pattern)
seqDict = self.extractDict(fileset)
print seqDict
seqlist = self.parseDict(seqDict)
#~ print seqlist
#~ total+=seqlist
cmds = self.genViewerCmds(seqlist)
#~ print cmds
return cmds
def get_tags_in_files(dicom_path, tag_file_path):
"""
get_tags_in_files iterates over a directory, finds dicom files with
a .dcm extension, and finds all unique dicom tag instances. it then
writes the tags out as a csv file.
Args:
dicom_path (str): Path to scan for dicom files.
tag_file_path (str): Path and file name for the output csv file.
Returns:
dict: A dictionary containing the tags loaded.
"""
# create the output directory
if not os.path.exists(os.path.dirname(tag_file_path)):
os.makedirs(os.path.dirname(tag_file_path))
# get the tags
tags_in_files = {}
dicom_file_paths = file_paths(
filtered_walk(dicom_path, included_files=["*.dcm"]))
for dicom_file_path in dicom_file_paths:
dicom_file = pydicom.read_file(dicom_file_path)
for item in dicom_file:
if item.keyword not in tags_in_files:
group = "0x%04x" % item.tag.group
element = "0x%04x" % item.tag.element
tags_in_files[
item.keyword] = group, element, item.keyword, item.name
# sort the tags
tags_in_files = OrderedDict(
sorted(tags_in_files.items(), key=(lambda k: (k[1][0], k[1][1]))))
# write out the file
with open(tag_file_path, "w") as f:
writer = csv.writer(f)
writer.writerow(["group", "element", "keyword", "name"])
for item in tags_in_files:
writer.writerow(tags_in_files[item])
return tags_in_files
def sequence(self, formats):
'''return final list'''
total = []
print 'iQuence Searching Path: %s' % self.topdir
fileset = file_paths(
filtered_walk(self.topdir,
depth=self.depth,
included_files=formats))
#~ print files
#for i in fileset: print i
#~ for pattern in formats:
#~ fileset = self.find_files(pattern)
seqDict = self.extractDict(fileset)
print seqDict
seqlist = self.parseDict(seqDict)
#~ print seqlist
#~ total+=seqlist
cmds = self.genViewerCmds(seqlist)
#~ print cmds
return cmds
def search(path):
"""
This method takes path to a directory as an argument and returns list of
files under it in the format:
filename: absolute path
"""
EXCLUDED_DIRS = ['env',
'venv',
'.git'
]
EXCLUDED_FILES = ['.gitignore',
'*.pyc',
'*.out'
]
files = {}
for i in file_paths(filtered_walk(path, excluded_dirs=EXCLUDED_DIRS,
excluded_files=EXCLUDED_FILES)):
files[os.path.basename(i)] = os.path.realpath(i)
return files
nbog + etnam
# In[21]:
#Write the blog post
#Ask to write content or publish
writecont = input('Write content? y/N ')
if 'y' in writecont:
contenmak = input('content: ')
else:
#search or manually locate fil.
pear = input('path to search: y/N')
if 'y' in pear:
files = file_paths(filtered_walk(pear, depth=100, included_files=[nbog + etnam]))
for fil in files:
print (fil)
jsve.update({'filefound' : fil})
else:
patlim = input('path of file: ')
jsve.update({'filefound' : patlim + nbog + etnam})
# In[22]:
#fil
# In[23]:
def get_file_paths(root_paths, extension='flac'):
pattern = '*.%s' % extension
for root in root_paths:
paths = file_paths(filtered_walk(root, included_files=[pattern]))
for file_path in paths:
yield file_path
runpy.run_module('requests')
# In[ ]:
# In[29]:
nbog = raw_input('Name of notebook to tag: ')
# In[30]:
files = file_paths(filtered_walk('/home/wcmckee/github/', depth=100, included_files=[nbog + '.ipynb']))
# In[35]:
#Easier to access ipynb and access the code import cell.
#Parse the notebook for import tags
#IPython module wrapper for returning list of imported modules
#from a ipynb file.
#Get the list of modules for tags from this.
# In[32]:
for fil in files:
#print fil
def index_podcasts():
files = file_paths(filtered_walk('static/podcasts', included_files=['*.mp3'], ))
return files
import os.path
from walkdir import filtered_walk, dir_paths, all_paths, file_paths
files = file_paths(filtered_walk('.', included_files=['*.go']))
packages = {}
for f in files:
dirn = os.path.dirname(f)
if dirn not in packages:
packages[dirn] = {}
packages[dirn][f] = 1
for n in packages:
print "{0}.o: {1}".format(n, " ".join(packages[n].keys()))
print "\t$(GCCGO) -L . -I . -c -g -o $@ $^"
print "all_pkgs:" + " ".join(["{}.o".format(n) for n in packages])
print "\teho"
