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

Fix youtube and embed links #14

Merged
merged 21 commits into from
Aug 27, 2021
Merged

Fix youtube and embed links #14

Show file tree
Hide file tree
Changes from 6 commits
Commits
Show all changes
21 commits
Select commit Hold shift + click to select a range
8e18cf6
Add in carriewright link splitting code
cansavvy Aug 25, 2021
92ddc63
Mapping things out
cansavvy Aug 25, 2021
4d8d022
Styled code, youtube -> watch
cansavvy Aug 25, 2021
dfcb9a0
Merge branch 'master' into cansavvy/link-splitters
cansavvy Aug 25, 2021
5604a53
Get rid of old scratch script "split_embed_links.R"
cansavvy Aug 25, 2021
004f8c2
Merge branch 'cansavvy/link-splitters' of https://github.com/jhudsl/l…
cansavvy Aug 25, 2021
4dab4a7
Adding youtube poster attribute
cansavvy Aug 25, 2021
d173d50
Get rid of old version of fix
cansavvy Aug 25, 2021
675d0ff
add stringr as dependency
cansavvy Aug 26, 2021
7ad1b4e
Add comma
cansavvy Aug 26, 2021
85c72ec
Add link to include_url()
cansavvy Aug 26, 2021
874a24e
Change wording of links
cansavvy Aug 26, 2021
74412a6
Merge branch 'master' into cansavvy/link-splitters
cansavvy Aug 26, 2021
94579ac
Get rid of stringr dependency
cansavvy Aug 26, 2021
7c50234
Add logic for ! or not
cansavvy Aug 26, 2021
91af811
Fixing logic
cansavvy Aug 26, 2021
155b18a
Fix some of the logic
cansavvy Aug 26, 2021
62eea5f
Revert "Get rid of stringr dependency"
cansavvy Aug 26, 2021
8641422
Revert "Revert "Get rid of stringr dependency""
cansavvy Aug 26, 2021
53fb9bd
Auto stash before revert of "Revert "Get rid of stringr dependency""
cansavvy Aug 26, 2021
7a05871
Fix logic around videos
cansavvy Aug 26, 2021
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
149 changes: 80 additions & 69 deletions R/aaa_utils.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,28 +2,28 @@
# get script path and number of paragraphs
paragraph_from_script <- function(x) {
if (file.exists(x)) {
para = readLines(x, warn = FALSE)
para = trimws(para)
para = para[!para %in% c("", " ")]
para <- readLines(x, warn = FALSE)
para <- trimws(para)
para <- para[!para %in% c("", " ")]
return(para)
} else{
} else {
return(NA)
}
}

n_para = function(x) {
x = paragraph_from_script(x)
n_para <- function(x) {
x <- paragraph_from_script(x)
if (length(x) == 0) {
return(0)
}
ifelse(all(is.na(x)), NA, length(x))
}

length0 = function(x) {
length0 <- function(x) {
length(x) == 0
}

length0_to_NA = function(x) {
length0_to_NA <- function(x) {
if (length0(x)) {
x <- NA
}
Expand All @@ -38,38 +38,39 @@ length0_to_NA = function(x) {
#' @return A scalar character vector
#' @export
#' @rdname gs_helpers
gs_id_from_slide = function(file) {
gs_id_from_slide <- function(file) {
if (!file.exists(file)) {
return(NA_character_)
}
x = readLines(file, warn = FALSE)
ind = grep(x, pattern = "\\[(S|s)lides\\]")
x <- readLines(file, warn = FALSE)
ind <- grep(x, pattern = "\\[(S|s)lides\\]")
if (length(ind) > 0) {
x = x[ind]
x <- x[ind]
} else {
x = x[grep(x, pattern = ".*presentation/d/")]

x <- x[grep(x, pattern = ".*presentation/d/")]
}
if (!any(grepl("http", x))) {
return(NA_character_)
}
x = sub(".*\\(\\s*(http.*)\\s*\\).*", "\\1", x)
x = unlist(sapply(x, function(r) httr::parse_url(r)$path))
x = sub("/edit$", "", x)
x = sub("/export/.*", "", x)
x = basename(x)
x = stats::na.omit(x)
x = x[ nchar(x) > 5 ]
ux = unique(x)
x <- sub(".*\\(\\s*(http.*)\\s*\\).*", "\\1", x)
x <- unlist(sapply(x, function(r) httr::parse_url(r)$path))
x <- sub("/edit$", "", x)
x <- sub("/export/.*", "", x)
x <- basename(x)
x <- stats::na.omit(x)
x <- x[nchar(x) > 5]
ux <- unique(x)
if (length(ux) > 1) {
warning(paste0("Multiple sheets identified! Taking most frequent.",
" Please check ",
file))
x = sort(table(x), decreasing = TRUE)
x = names(x)[1]
warning(paste0(
"Multiple sheets identified! Taking most frequent.",
" Please check ",
file
))
x <- sort(table(x), decreasing = TRUE)
x <- names(x)[1]
# x = x[1]
} else {
x = ux
x <- ux
}
if (length(x) == 0 || grepl("\\(\\)", x)) {
return(NA_character_)
Expand All @@ -85,10 +86,10 @@ gs_id_from_slide = function(file) {
######################################
#' @export
#' @rdname gs_helpers
get_image_link_from_slide = function(file) {
x = readLines(file, warn = FALSE)
x = grep(x, pattern = "!\\[.*\\]\\(((resources/|)images.*)\\)", value = TRUE)
x = sub(x, pattern = "!\\[(.*)\\]\\(((resources/|)images.*)\\)", replacement = "\\1")
get_image_link_from_slide <- function(file) {
x <- readLines(file, warn = FALSE)
x <- grep(x, pattern = "!\\[.*\\]\\(((resources/|)images.*)\\)", value = TRUE)
x <- sub(x, pattern = "!\\[(.*)\\]\\(((resources/|)images.*)\\)", replacement = "\\1")
# if (length(x) == 0) {
# return(NA)
# }
Expand All @@ -101,61 +102,68 @@ get_image_link_from_slide = function(file) {
######################################
#' @export
#' @rdname gs_helpers
get_image_from_slide = function(file) {
x = readLines(file, warn = FALSE)
x = grep(x, pattern = "!\\[.*\\]\\(((resources/|)images.*)\\)", value = TRUE)
x = sub(x, pattern = "!\\[.*\\]\\(((resources/|)images.*)\\)", replacement = "\\1")
get_image_from_slide <- function(file) {
x <- readLines(file, warn = FALSE)
x <- grep(x, pattern = "!\\[.*\\]\\(((resources/|)images.*)\\)", value = TRUE)
x <- sub(x, pattern = "!\\[.*\\]\\(((resources/|)images.*)\\)", replacement = "\\1")
# if (length(x) == 0) {
# return(NA)
# }
return(x)
}


list_one_file = function(x, ending = "pdf") {
pdfs = list.files(
list_one_file <- function(x, ending = "pdf") {
pdfs <- list.files(
pattern = paste0("[.]", ending),
path = x,
full.names = TRUE)
full.names = TRUE
)
if (length(pdfs) > 1) {
warning(paste0(x, " had more than one ", ending, "! ",
"Only grabbing first"))
pdfs = pdfs[1]
warning(paste0(
x, " had more than one ", ending, "! ",
"Only grabbing first"
))
pdfs <- pdfs[1]
}
pdfs = length0_to_NA(pdfs)
pdfs <- length0_to_NA(pdfs)
return(pdfs)
}




png_pattern = function() {
paste0("^!\\[.+\\]\\((?!\\.png)\\)|",
"^!\\[\\]\\((?!\\.png)\\)|",
"^!\\[.+\\]\\((?!\\.png)\\)|",
"!\\[.+\\]\\(.+[^.png]\\)|",
"^!\\[.+\\]\\(https\\:\\/\\/www\\.youtu.+\\)")
png_pattern <- function() {
paste0(
"^!\\[.+\\]\\((?!\\.png)\\)|",
"^!\\[\\]\\((?!\\.png)\\)|",
"^!\\[.+\\]\\((?!\\.png)\\)|",
"!\\[.+\\]\\(.+[^.png]\\)|",
"^!\\[.+\\]\\(https\\:\\/\\/www\\.youtu.+\\)"
)
}

yt_pattern = function() {
paste0("^!\\[.+\\]\\(https\\:\\/\\/www\\.youtu.+\\)|",
"^!\\[.+\\]\\(https\\:\\/\\/youtu.+\\)")
yt_pattern <- function() {
paste0(
"^!\\[.+\\]\\(https\\:\\/\\/www\\.youtu.+\\)|",
"^!\\[.+\\]\\(https\\:\\/\\/youtu.+\\)"
)
}

is.Token = function(token) {
is.Token <- function(token) {
inherits(token, "Token") ||
(inherits(token, "request") &&
inherits(token$auth_token, "Token"))
inherits(token$auth_token, "Token"))
}


na_false = function(test) {
test[ is.na(test)] = FALSE
na_false <- function(test) {
test[is.na(test)] <- FALSE
test
}

na_true = function(test) {
test[ is.na(test)] = TRUE
na_true <- function(test) {
test[is.na(test)] <- TRUE
test
}

Expand All @@ -180,24 +188,27 @@ sys_type <- function() {
}


png_url = function(id, page_id) {
png_url <- function(id, page_id) {
paste0(
"https://docs.google.com/presentation/d/",
id, "/export/png?id=", id,
"&pageid=", page_id)
"&pageid=", page_id
)
}

download_png_urls = function(urls) {
res = vapply(urls, function(url) {
tfile = tempfile(fileext = ".png")
out = httr::GET(url, httr::write_disk(tfile),
httr::content_type(".png"))
download_png_urls <- function(urls) {
res <- vapply(urls, function(url) {
tfile <- tempfile(fileext = ".png")
out <- httr::GET(
url, httr::write_disk(tfile),
httr::content_type(".png")
)
httr::stop_for_status(out)
ctype = out$headers$`content-type`
ctype = strsplit(ctype, " ")[[1]]
ctype = sub(";$", "", ctype)
ctype <- out$headers$`content-type`
ctype <- strsplit(ctype, " ")[[1]]
ctype <- sub(";$", "", ctype)
if (any(ctype == "text/html") &&
!any(grepl("png", ctype))) {
!any(grepl("png", ctype))) {
stop("Output is not a PNG!")
}
tfile
Expand Down
Loading