From 460bc00698ec31ef95c523011d64b2ea38898cf3 Mon Sep 17 00:00:00 2001
From: Fabian Homborg <FHomborg@gmail.com>
Date: Wed, 7 Nov 2018 12:37:47 +0100
Subject: [PATCH] Fix string escape var and url styles

Turns out I broke these in my zeal to remove wcs2string.

This reverts commit 583d771b106970863230f8df68d2c36b601db8b9.

Fixes #5322.
---
 src/common.cpp   | 16 ++++++++++------
 tests/string.err |  7 +++++--
 tests/string.in  | 11 +++++++++++
 tests/string.out | 11 +++++++++++
 4 files changed, 37 insertions(+), 8 deletions(-)

diff --git a/src/common.cpp b/src/common.cpp
index 038e6ead6..7160ef978 100644
--- a/src/common.cpp
+++ b/src/common.cpp
@@ -820,7 +820,8 @@ wcstring reformat_for_screen(const wcstring &msg) {
 
 /// Escape a string in a fashion suitable for using as a URL. Store the result in out_str.
 static void escape_string_url(const wcstring &in, wcstring &out) {
-    for (auto &c1 : in) {
+    const std::string narrow = wcs2string(in);
+    for (auto &c1 : narrow) {
         // This silliness is so we get the correct result whether chars are signed or unsigned.
         unsigned int c2 = (unsigned int)c1 & 0xFF;
         if (!(c2 & 0x80) &&
@@ -871,22 +872,25 @@ static bool unescape_string_url(const wchar_t *in, wcstring *out) {
 /// Escape a string in a fashion suitable for using as a fish var name. Store the result in out_str.
 static void escape_string_var(const wcstring &in, wcstring &out) {
     bool prev_was_hex_encoded = false;
-    for (auto c1 : in) {
-        if (c1 >= 0 && c1 <= 127 && isalnum(c1) && (!prev_was_hex_encoded || !is_hex_digit(c1))) {
+    const std::string narrow = wcs2string(in);
+    for (auto c1 : narrow) {
+        // This silliness is so we get the correct result whether chars are signed or unsigned.
+        unsigned int c2 = (unsigned int)c1 & 0xFF;
+        if (!(c2 & 0x80) && isalnum(c2) && (!prev_was_hex_encoded || !is_hex_digit(c2))) {
             // ASCII alphanumerics don't need to be encoded.
             if (prev_was_hex_encoded) {
                 out.push_back(L'_');
                 prev_was_hex_encoded = false;
             }
-            out.push_back(c1);
-        } else if (c1 == L'_') {
+            out.push_back((wchar_t)c2);
+        } else if (c2 == '_') {
             // Underscores are encoded by doubling them.
             out.append(L"__");
             prev_was_hex_encoded = false;
         } else {
             // All other chars need to have their UTF-8 representation encoded in hex.
             wchar_t buf[4];
-            swprintf(buf, sizeof buf / sizeof buf[0], L"_%02X", c1);
+            swprintf(buf, sizeof buf / sizeof buf[0], L"_%02X", c2);
             out.append(buf);
             prev_was_hex_encoded = true;
         }
diff --git a/tests/string.err b/tests/string.err
index 890f6a00c..b016d450d 100644
--- a/tests/string.err
+++ b/tests/string.err
@@ -89,6 +89,9 @@
 ####################
 # string escape --style=var -- -
 
+####################
+# string escape with multibyte chars
+
 ####################
 # set x (string unescape (echo \x07 | string escape))
 
@@ -179,7 +182,7 @@ string match: ^
 ####################
 # string invalidarg
 string: Subcommand 'invalidarg' is not valid
-Standard input (line 194): 
+Standard input (line 205): 
 string invalidarg; and echo "unexpected exit 0"
 ^
 
@@ -264,7 +267,7 @@ string repeat: Expected argument
 ####################
 # string repeat -l fakearg 2>&1
 string repeat: Unknown option '-l'
-Standard input (line 270): 
+Standard input (line 281): 
 string repeat -l fakearg
 ^
 
diff --git a/tests/string.in b/tests/string.in
index f267a1952..fc6be1bbf 100644
--- a/tests/string.in
+++ b/tests/string.in
@@ -90,6 +90,17 @@ string escape --style=var '_a_b_c_'
 logmsg 'string escape --style=var -- -'
 string escape --style=var -- -
 
+logmsg 'string escape with multibyte chars'
+string escape --style=url aöb
+string escape --style=url 中
+string escape --style=url aöb | string unescape --style=url
+string escape --style=url 中 | string unescape --style=url
+
+string escape --style=var aöb
+string escape --style=var 中
+string escape --style=var aöb | string unescape --style=var
+string escape --style=var 中 | string unescape --style=var
+
 # The following tests verify that we can correctly unescape the same strings
 # we tested escaping above.
 
diff --git a/tests/string.out b/tests/string.out
index d9de63114..a10e6010d 100644
--- a/tests/string.out
+++ b/tests/string.out
@@ -129,6 +129,17 @@ __a__b__c__
 # string escape --style=var -- -
 _2D_
 
+####################
+# string escape with multibyte chars
+a%C3%B6b
+%E4%B8%AD
+aöb
+中
+a_C3_B6_b
+_E4_B8_AD_
+aöb
+中
+
 ####################
 # set x (string unescape (echo \x07 | string escape))
 success