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

Do not escape comments #110

Merged
merged 2 commits into from
Apr 6, 2016
Merged

Do not escape comments #110

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cd0beec
Do not escape comments (but still sanitize them).
Drup Apr 2, 2016
e82852f
Add escaping tests for comments.
Drup Apr 2, 2016
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
2 changes: 1 addition & 1 deletion _oasis
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,7 @@ Library tyxml_f
Html5_sigs,
Html5_types,
Html5_f
BuildDepends: uutf
BuildDepends: uutf, re

Library tyxml_top
FindlibName: top
Expand Down
59 changes: 36 additions & 23 deletions lib/xml_print.ml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,16 +48,39 @@ let encode_unsafe_char_and_at s =
Buffer.contents b

let compose_decl ?(version = "1.0") ?(encoding = "UTF-8") () =
"<?xml version=\"" ^ version ^ "\" encoding=\"" ^ encoding ^ "\"?>\n"
Format.sprintf
{|<?xml version="%s" encoding="%s"?>\n|}
version encoding

let compose_doctype dt args =
"<!DOCTYPE " ^ dt
^ (if args = []
then ""
else
" PUBLIC " ^
String.concat " " (List.map (fun a -> "\"" ^ a ^ "\"") args)) ^ ">"

let pp_args fmt = function
| [] -> ()
| l ->
Format.fprintf fmt " PUBLIC %a"
(Format.pp_print_list ~pp_sep:Format.pp_print_space
(fun fmt -> Format.fprintf fmt "%S"))
l
in
Format.asprintf
"<!DOCTYPE %s%a>"
dt
pp_args args

let re_end_comment = Re.(compile @@ alt [
seq [ bos ; str ">" ] ;
seq [ bos ; str "->" ] ;
str "-->" ;
str "--!>" ;
])
let escape_comment s =
let f g = match Re.Group.get g 0 with
| ">" -> "&gt;"
| "->" -> "-&gt;"
| "-->" -> "--&gt;"
| "--!>" -> "--!&gt;"
| s -> s
in
Re.replace ~all:true re_end_comment ~f s

(* copied form js_of_ocaml: compiler/javascript.ml *)
let pp_number fmt v =
Expand Down Expand Up @@ -177,16 +200,6 @@ module type TagList = sig val emptytags : string list end

let pp_noop _fmt _ = ()

(* Present only in ocaml >= 4.02 *)
let rec pp_print_list ~pp_sep pp_v ppf = function
| [] -> ()
| [v] -> pp_v ppf v
| v :: vs ->
pp_v ppf v;
pp_sep ppf ();
pp_print_list ~pp_sep pp_v ppf vs


module Make_fmt
(Xml : Xml_sigs.Iterable)
(I : TagList) =
Expand All @@ -213,14 +226,14 @@ struct
| AStr s -> Format.fprintf fmt "%S" (encode s)
| AStrL (sep, slist) ->
Format.fprintf fmt "\"%a\""
(pp_print_list ~pp_sep:(pp_sep sep) (pp_encode encode)) slist
(Format.pp_print_list ~pp_sep:(pp_sep sep) (pp_encode encode)) slist

let pp_attrib encode fmt a =
Format.fprintf fmt
" %s=%a" (aname a) (pp_attrib_value encode) a

let pp_attribs encode =
pp_print_list ~pp_sep:pp_noop (pp_attrib encode)
Format.pp_print_list ~pp_sep:pp_noop (pp_attrib encode)

let pp_closedtag encode fmt tag attrs =
if is_emptytag tag then
Expand All @@ -240,13 +253,13 @@ struct

and pp_elt encode fmt elt = match content elt with
| Comment texte ->
Format.fprintf fmt "<!--%a-->" (pp_encode encode) texte
Format.fprintf fmt "<!--%s-->" (escape_comment texte)

| Entity e ->
Format.fprintf fmt "&%s;" e

| PCDATA texte ->
Format.pp_print_string fmt (encode texte)
pp_encode encode fmt texte

| EncodedPCDATA texte ->
Format.pp_print_string fmt texte
Expand All @@ -260,7 +273,7 @@ struct
| Empty -> ()

and pp_elts encode =
pp_print_list ~pp_sep:pp_noop (pp_elt encode)
Format.pp_print_list ~pp_sep:pp_noop (pp_elt encode)

let pp ?(encode=encode_unsafe_char) () =
pp_elt encode
Expand Down
21 changes: 21 additions & 0 deletions test/test_html.ml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,6 +53,27 @@ let escaping = "html escaping", tyxml_tests Html5.[
/* ]]> */
|} ;

"comment",
tot (Xml.comment
{|[if IE 8]> <html class="no-js lt-ie9" lang="en"> <![endif]|}),
{|<!--[if IE 8]> <html class="no-js lt-ie9" lang="en"> <![endif]-->|} ;

"dodgy comment 1",
tot (Xml.comment {|><script BOUM/>|}),
{|<!--&gt;<script BOUM/>-->|} ;

"dodgy comment 2",
tot (Xml.comment {|-><script BOUM/>|}),
{|<!---&gt;<script BOUM/>-->|} ;

"dodgy comment 3",
tot (Xml.comment {|foo--><script BOUM/>|}),
{|<!--foo--&gt;<script BOUM/>-->|} ;

"dodgy comment 4",
tot (Xml.comment {|foo--!><script BOUM/>|}),
{|<!--foo--!&gt;<script BOUM/>-->|} ;

]


Expand Down