Skip to content

Strip quotes in detect-charset #618

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

Open
wants to merge 1 commit into
base: 3.x
Choose a base branch
from
Open

Strip quotes in detect-charset #618

Show file tree
Hide file tree
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
11 changes: 10 additions & 1 deletion src/clj_http/client.clj
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -756,13 +756,22 @@
([req respond raise]
(client (accept-encoding-request req) respond raise))))

(defn- strip-quotes
"If s starts and ends with \", returns s with quotes stripped,
else returns it unchanged."
[^String s]
(if (and (.startsWith s "\"")
(.endsWith s "\""))
(subs s 1 (dec (count s)))
s))

(defn detect-charset
"Given a charset header, detect the charset, returns UTF-8 if not found."
[content-type]
(or
(when-let [found (when content-type
(re-find #"(?i)charset\s*=\s*([^\s]+)" content-type))]
(second found))
(strip-quotes (second found)))
"UTF-8"))

(defn- multi-param-entries [key values multi-param-style encoding]
Expand Down
18 changes: 9 additions & 9 deletions test/clj_http/test/client_test.clj
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1633,15 +1633,15 @@
client/wrap-request-timing))))

(deftest t-detect-charset-by-content-type
(is (= "UTF-8" (client/detect-charset nil)))
(is (= "UTF-8"(client/detect-charset "application/json")))
(is (= "UTF-8"(client/detect-charset "text/html")))
(is (= "GBK"(client/detect-charset "application/json; charset=GBK")))
(is (= "ISO-8859-1" (client/detect-charset
"application/json; charset=ISO-8859-1")))
(is (= "ISO-8859-1" (client/detect-charset
"application/json; charset = ISO-8859-1")))
(is (= "GB2312" (client/detect-charset "text/html; Charset=GB2312"))))
(are [content-type expected-charset] (= expected-charset (client/detect-charset content-type))
nil "UTF-8"
"application/json" "UTF-8"
"text/html" "UTF-8"
"application/json; charset=GBK" "GBK"
"application/json; charset=ISO-8859-1" "ISO-8859-1"
"application/json; charset = ISO-8859-1" "ISO-8859-1"
"text/html; Charset=GB2312" "GB2312"
"text/html; charset=\"ISO-8859-1\"" "ISO-8859-1"))

(deftest ^:integration customMethodTest
(run-server)
Expand Down