Git commits

Download: git_commits_evol.csv.gz

data <- read.csv(file=url_git_commits, header=T)

File is git_commits_evol.csv, and has 3 columns for 4643 commits.

data$commits_sum <- cumsum(data$commits)
data.xts <- xts(x = data[,c('commits_sum', 'commits', 'authors')], order.by=as.POSIXct(as.character(data[,c('date')]), format="%Y-%m-%d"))

p <-dygraph(data.xts[,c('commits')],
        main = paste('Daily commits for ', project_id, sep=''),
        width = 800, height = 250 ) %>%
      dyRangeSelector()
p

Git log

Download: git_log.txt.gz

File is git_log.txt, and full log has 187014 lines.

Bugzilla issues

Download: bugzilla_issues.csv.gz

data <- read.csv(file=url_bz_issues, header=T)

File is bugzilla_issues.csv, and has 17 columns for 21101 issues.

Bugzilla open issues

Download: bugzilla_issues_open.csv.gz

data <- read.csv(file=url_bz_issues_open, header=T)

File is bugzilla_issues_open.csv, and has 17 columns for 4682 issues (all open).

Bugzilla evolution

Download: bugzilla_evol.csv.gz

data <- read.csv(file=url_bz_evol, header=T)

File is bugzilla_evol.csv, and has 3 columns for 4902 weeks.

data.xts <- xts(x = data, order.by = as.POSIXct(data$date))
data.monthly <- apply.monthly(x=data.xts, FUN = nrow)

p <-dygraph(data.monthly[,1],
        main = paste('Monthly issues submissions for ', project_id, sep=''),
        width = "750px", height = 250 ) %>%
      dyRangeSelector()
p

Versions

Download: bugzilla_versions.csv.gz

data <- read.csv(file=url_bz_versions, header=T)

File is bugzilla_versions.csv, and has 2 columns for 66 weeks.

Components

Download: bugzilla_components.csv.gz

data <- read.csv(file=url_bz_components, header=T)

File is bugzilla_components.csv, and has 2 columns for 27 weeks.

Forums posts

Download: eclipse_forums_posts.csv.gz

data <- read.csv(file=url_forums_posts, header=T)

File is ../scripts/projects/tools.cdt/eclipse_forums_posts.csv, and has 6 columns for 37840 posts. The evolution of posts

data$created.date <- as.POSIXct(data$created_date, origin="1970-01-01")
posts.xts <- xts(data, order.by = data$created.date)
posts.weekly <- apply.weekly(x=posts.xts, FUN = nrow)
names(posts.weekly) <- c("posts")

p <- dygraph(
  data = posts.weekly,
  main = paste('Weekly forum posts for ', project_id, sep=''),
  width = 800, height = 250 ) %>%
  dyAxis("x", drawGrid = FALSE) %>%
  dySeries("posts", label = "Weekly posts") %>%
  dyOptions(stepPlot = TRUE) %>%
  dyRangeSelector()
p

The list of the 10 last active posts on the forums:

data$created.date <- as.POSIXct(data$created_date, origin="1970-01-01")
posts.table <- head(data[,c('id', 'subject', 'created.date', 'author_id')], 10)
posts.table$subject <- paste('<a href="', posts.table$html_url, '">', posts.table$subject, '</a>', sep='')
posts.table$created.date <- as.character(posts.table$created.date)
names(posts.table) <- c('ID', 'Subject', 'Post date', 'Post author')

print(
    xtable(head(posts.table, 10),
        caption = paste('10 most recent posts on', project_id, 'forum.', sep=" "),
        digits=0, align="lllll"), type="html",
    html.table.attributes='class="table table-striped"',
    caption.placement='bottom',
    include.rownames=FALSE,
    sanitize.text.function=function(x) { x }
)

Forums threads

Download: eclipse_forums_threads.csv.gz

data <- read.csv(file=url_forums_threads, header=T)

File is ../scripts/projects/tools.cdt/eclipse_forums_threads.csv, and has 8 columns for 13513 threads. A wordcloud with the main words used in threads is presented below.

The list of the 10 last active threads on the forums:

data$last.post.date <- as.POSIXct(data$last_post_date, origin="1970-01-01")
threads.table <- head(data[,c('id', 'subject', 'last.post.date', 'last_post_id', 'replies', 'views')], 10)
threads.table$subject <- paste('<a href="', threads.table$html_url, '">', threads.table$subject, '</a>', sep='')
threads.table$last.post.date <- as.character(threads.table$last.post.date)
names(threads.table) <- c('ID', 'Subject', 'Last post date', 'Last post author', 'Replies', 'Views')

print(
    xtable(threads.table,
        caption = paste('10 last active threads on', project_id, 'forum.', sep=" "),
        digits=0, align="lllllll"), type="html",
    html.table.attributes='class="table table-striped"',
    caption.placement='bottom',
    include.rownames=FALSE,
    sanitize.text.function=function(x) { x }
)

PMI Checks

Download: eclipse_pmi_checks.csv.gz

data <- read.csv(file=url_pmi_checks, header=T)

File is eclipse_pmi_checks.csv, and has 3 columns for 17 commits.

checks.table <- head(data[,c('Description', 'Value', 'Results')], 10)

print(
    xtable(checks.table,
        caption = paste('Extract of the 10 first PMI checks for ', 
                        project_id, '.', sep=" "),
        digits=0, align="llll"), type="html",
    html.table.attributes='class="table table-striped"',
    caption.placement='bottom',
    include.rownames=FALSE,
    sanitize.text.function=function(x) { x }
)

SonarQube blocker issues

Download: sq_issues_blocker.csv.gz

data <- read.csv(file=url_sq_issues_blocker, header=T)

File is sq_issues_blocker.csv, and has 5 columns for 140 issues.

data$last.update <- as.POSIXct(data$last_update, origin="1970-01-01")
issues.table <- head(data[,c('key', 'rule', 'sev', 'last.update', 'message')], 10)
issues.table$last.update <- as.character(issues.table$last.update)
names(issues.table) <- c('Key', 'Rule', 'Severity', 'Last update', 'Message')

print(
    xtable(issues.table,
        caption = paste('Extract of 10 SonarQube blocker issues for ', 
                        project_id, '.', sep=" "),
        digits=0, align="llllll"), type="html",
    html.table.attributes='class="table table-striped"',
    caption.placement='bottom',
    include.rownames=FALSE,
    sanitize.text.function=function(x) { x }
)

SonarQube critical issues

Download: sq_issues_critical.csv.gz

data <- read.csv(file=url_sq_issues_critical, header=T)

File is sq_issues_critical.csv, and has 5 columns for 500 issues.

SonarQube major issues

Download: sq_issues_major.csv.gz

data <- read.csv(file=url_sq_issues_major, header=T)

File is sq_issues_major.csv, and has 5 columns for 500 issues.

SonarQube metrics

Download: sq_metrics.csv.gz

data <- read.csv(file=url_sq_metrics, header=T)

File is sq_metrics.csv, and has 45 columns for 1 line.

# Transform from wide to long format.
data <- t(data)
data_ <- data.frame(rownames(data), data[,1])
names(data_) <- c('Metric', 'Value')
# Remove NAs
data_  <- data_[complete.cases(data_$Value),]

print(
    xtable(data_,
        caption = paste('SonarQube metrics for ', 
                        project_id, '.', sep=" "),
        digits=0, align="lll"), type="html",
    html.table.attributes='class="table table-striped"',
    caption.placement='bottom',
    include.rownames=FALSE,
    sanitize.text.function=function(x) { x }
)