def graphNewcomers(repoPath, newcomers):
# Sometimes we get bad data?
newcomers = [x for x in newcomers if len(x.split('\t')) >= 4]
issue = [x for x in newcomers if x.split('\t')[2].startswith('issue')]
comment = [x for x in newcomers if x.split('\t')[2].startswith('comment')]
pull = [x for x in newcomers if jsonIsPullRequest(x.split('\t')[2])]
commentPR = [
x for x in newcomers if jsonIsPullRequestComment(x.split('\t')[2])
]
# For each line, pull out the filename (third item)
data = [
Bar(
x=[
'Opened an issue',
'Commented on an issue<BR>opened by someone else',
'Opened a pull request',
'Commented on a pull request<BR>opened by someone else'
],
y=[len(issue), len(comment),
len(pull), len(commentPR)],
)
]
layout = Layout(title='First contribution types for<BR>' + repoPath, )
fig = Figure(data=data, layout=layout)
return offline.plot(fig,
show_link=False,
include_plotlyjs=False,
output_type='div')
def separatePRs(repoPath, username, cutoff):
interaction = []
noInteraction = []
# Save the pr-*.txt filenames where username commented
# in the comment or pr-comment
for directory in os.listdir(repoPath):
if not os.path.isdir(os.path.join(repoPath, directory)):
continue
match = False
files = os.listdir(os.path.join(repoPath, directory))
prFile = [x for x in files if jsonIsPullRequest(x)]
if not prFile:
continue
# Figure out whether this pull request was merged or not
with open(os.path.join(repoPath, directory, prFile[0])) as f:
prSoup = json.load(f)
if cutoff and datetime.strptime(prSoup['created_at'],
"%Y-%m-%dT%H:%M:%SZ") < cutoff:
continue
if not prSoup['merged']:
merged = 0
seconds = None
else:
merged = 1
ctime = datetime.strptime(prSoup['created_at'],
"%Y-%m-%dT%H:%M:%SZ")
mtime = datetime.strptime(prSoup['merged_at'],
"%Y-%m-%dT%H:%M:%SZ")
seconds = (mtime - ctime).total_seconds()
if (seconds < 0):
print("WARN: PR", os.path.join(repoPath, directory, prFile[0]),
"merged before it was created?")
print("Created", ctime)
print("Merged", mtime)
seconds = 0
# Figure out if username made an issue or pr comment
comments = [
x for x in files
if jsonIsPullRequestComment(x) or x.startswith('comment-')
]
for cfile in comments:
with open(os.path.join(repoPath, directory, cfile)) as commentFile:
soup = json.load(commentFile)
user, date = getUserDate(soup)
if user == username:
match = True
if match:
interaction.append((os.path.join(repoPath,
directory), merged, seconds))
else:
noInteraction.append((os.path.join(repoPath,
directory), merged, seconds))
return interaction, noInteraction
def separateByDate(repoPath, cutoff, startDate, endDate):
older = []
newer = []
for directory in os.listdir(repoPath):
if not os.path.isdir(os.path.join(repoPath, directory)):
continue
match = False
files = os.listdir(os.path.join(repoPath, directory))
prFile = [x for x in files if jsonIsPullRequest(x)]
if not prFile:
continue
# Figure out whether this pull request was merged or not
with open(os.path.join(repoPath, directory, prFile[0])) as f:
prSoup = json.load(f)
if not prSoup['merged']:
merged = 0
seconds = None
else:
merged = 1
ctime = datetime.strptime(prSoup['created_at'],
"%Y-%m-%dT%H:%M:%SZ")
mtime = datetime.strptime(prSoup['merged_at'],
"%Y-%m-%dT%H:%M:%SZ")
seconds = (mtime - ctime).total_seconds()
if (seconds < 0):
print("WARN: PR", os.path.join(repoPath, directory, prFile[0]),
"merged before it was created?")
print("Created", ctime)
print("Merged", mtime)
seconds = 0
else:
# Convert to hours, to make graphs easier to read
seconds = seconds / (60. * 60)
if (startDate and ctime < startDate) or (endDate and ctime > endDate):
continue
if ctime < cutoff:
older.append((os.path.join(repoPath, directory), merged, seconds))
else:
newer.append((os.path.join(repoPath, directory), merged, seconds))
return older, newer