[Qemu-devel] [PATCH v6 03/15] qapi: Factor out JSON string escaping

[Eric Blake]

Pull out a new qstring_append_json_string() helper, so that all
JSON output producers can use the same output escaping rules.

While it appears that vmstate's use of the simpler qjson.c
formatter is not currently encountering any string that needs
escapes to be valid JSON, it is better to be safe than sorry,
and this substitution is not adding any potential asserts
during migration.

Adding a return value will let callers that care diagnose the
situation where an attempt was made to output invalid JSON (we
use substitute characters, and in fact guarantee that our
output is ASCII via escapes even if the input was UTF-8).  None
of the current callers care, but a future patch wants to make
it possible to conditionally turn this situation into an error.

Signed-off-by: Eric Blake <address@hidden>

---
v6: comment tweaks
[no v5 due to series split]
v4: keep helper in qobject-json.[ch], tweak variable name and
for loop iterator, add return value, drop R-b
v3: rebase to include cleanups in master
v2: no change
---
 include/qapi/qmp/qjson.h |   2 +
 migration/qjson.c        |  10 ++--
 qobject/qjson.c          | 126 ++++++++++++++++++++++++++---------------------
 3 files changed, 76 insertions(+), 62 deletions(-)

diff --git a/include/qapi/qmp/qjson.h b/include/qapi/qmp/qjson.h
index 02b1f2c..aa8ddd7 100644
--- a/include/qapi/qmp/qjson.h
+++ b/include/qapi/qmp/qjson.h
@@ -24,4 +24,6 @@ QObject *qobject_from_jsonv(const char *string, va_list *ap) 
GCC_FMT_ATTR(1, 0);
 QString *qobject_to_json(const QObject *obj);
 QString *qobject_to_json_pretty(const QObject *obj);

+int qstring_append_json_string(QString *qstring, const char *str);
+
 #endif /* QJSON_H */
diff --git a/migration/qjson.c b/migration/qjson.c
index f345904..741f9e6 100644
--- a/migration/qjson.c
+++ b/migration/qjson.c
@@ -26,6 +26,7 @@
 #include "qemu/osdep.h"
 #include "qapi/qmp/qstring.h"
 #include "migration/qjson.h"
+#include "qapi/qmp/qjson.h"

 struct QJSON {
     QString *str;
@@ -42,9 +43,8 @@ static void json_emit_element(QJSON *json, const char *name)
     }

     if (name) {
-        qstring_append(json->str, "\"");
-        qstring_append(json->str, name);
-        qstring_append(json->str, "\" : ");
+        qstring_append_json_string(json->str, name);
+        qstring_append(json->str, " : ");
     }
 }

@@ -83,9 +83,7 @@ void json_prop_int(QJSON *json, const char *name, int64_t val)
 void json_prop_str(QJSON *json, const char *name, const char *str)
 {
     json_emit_element(json, name);
-    qstring_append_chr(json->str, '"');
-    qstring_append(json->str, str);
-    qstring_append_chr(json->str, '"');
+    qstring_append_json_string(json->str, str);
 }

 const char *qjson_get_str(QJSON *json)
diff --git a/qobject/qjson.c b/qobject/qjson.c
index 906a8fc..6810726 100644
--- a/qobject/qjson.c
+++ b/qobject/qjson.c
@@ -82,7 +82,6 @@ static void to_json(const QObject *obj, QString *str, int 
pretty, int indent);
 static void to_json_dict_iter(const char *key, QObject *obj, void *opaque)
 {
     ToJsonIterState *s = opaque;
-    QString *qkey;
     int j;

     if (s->count) {
@@ -95,9 +94,7 @@ static void to_json_dict_iter(const char *key, QObject *obj, 
void *opaque)
             qstring_append(s->str, "    ");
     }

-    qkey = qstring_from_str(key);
-    to_json(QOBJECT(qkey), s->str, s->pretty, s->indent);
-    QDECREF(qkey);
+    qstring_append_json_string(s->str, key);

     qstring_append(s->str, ": ");
     to_json(obj, s->str, s->pretty, s->indent);
@@ -139,58 +136,9 @@ static void to_json(const QObject *obj, QString *str, int 
pretty, int indent)
     }
     case QTYPE_QSTRING: {
         QString *val = qobject_to_qstring(obj);
-        const char *ptr;
-        int cp;
-        char buf[16];
-        char *end;
-
-        ptr = qstring_get_str(val);
-        qstring_append(str, "\"");
-
-        for (; *ptr; ptr = end) {
-            cp = mod_utf8_codepoint(ptr, 6, &end);
-            switch (cp) {
-            case '\"':
-                qstring_append(str, "\\\"");
-                break;
-            case '\\':
-                qstring_append(str, "\\\\");
-                break;
-            case '\b':
-                qstring_append(str, "\\b");
-                break;
-            case '\f':
-                qstring_append(str, "\\f");
-                break;
-            case '\n':
-                qstring_append(str, "\\n");
-                break;
-            case '\r':
-                qstring_append(str, "\\r");
-                break;
-            case '\t':
-                qstring_append(str, "\\t");
-                break;
-            default:
-                if (cp < 0) {
-                    cp = 0xFFFD; /* replacement character */
-                }
-                if (cp > 0xFFFF) {
-                    /* beyond BMP; need a surrogate pair */
-                    snprintf(buf, sizeof(buf), "\\u%04X\\u%04X",
-                             0xD800 + ((cp - 0x10000) >> 10),
-                             0xDC00 + ((cp - 0x10000) & 0x3FF));
-                } else if (cp < 0x20 || cp >= 0x7F) {
-                    snprintf(buf, sizeof(buf), "\\u%04X", cp);
-                } else {
-                    buf[0] = cp;
-                    buf[1] = 0;
-                }
-                qstring_append(str, buf);
-            }
-        };
-
-        qstring_append(str, "\"");
+        /* FIXME: no way inform user if we replaced invalid UTF-8
+         * sequences to avoid invalid JSON */
+        qstring_append_json_string(str, qstring_get_str(val));
         break;
     }
     case QTYPE_QDICT: {
@@ -290,3 +238,69 @@ QString *qobject_to_json_pretty(const QObject *obj)

     return str;
 }
+
+/**
+ * Append a JSON string to @qstring that encodes the C string @str.
+ *
+ * @str is in UTF-8.  The JSON string is enclosed in double quotes and
+ * has funny characters escaped.  Invalid UTF-8 sequences are replaced
+ * by (properly escaped) U+0xFFFD replacement characters. Return -1 if
+ * invalid sequences were replaced, else 0.
+ */
+int qstring_append_json_string(QString *qstring, const char *str)
+{
+    const char *ptr;
+    int cp;
+    char buf[16];
+    char *end;
+    int result = 0;
+
+    qstring_append(qstring, "\"");
+
+    for (ptr = str; *ptr; ptr = end) {
+        cp = mod_utf8_codepoint(ptr, 6, &end);
+        switch (cp) {
+        case '\"':
+            qstring_append(qstring, "\\\"");
+            break;
+        case '\\':
+            qstring_append(qstring, "\\\\");
+            break;
+        case '\b':
+            qstring_append(qstring, "\\b");
+            break;
+        case '\f':
+            qstring_append(qstring, "\\f");
+            break;
+        case '\n':
+            qstring_append(qstring, "\\n");
+            break;
+        case '\r':
+            qstring_append(qstring, "\\r");
+            break;
+        case '\t':
+            qstring_append(qstring, "\\t");
+            break;
+        default:
+            if (cp < 0) {
+                cp = 0xFFFD; /* replacement character */
+                result = -1;
+            }
+            if (cp > 0xFFFF) {
+                /* beyond BMP; need a surrogate pair */
+                snprintf(buf, sizeof(buf), "\\u%04X\\u%04X",
+                         0xD800 + ((cp - 0x10000) >> 10),
+                         0xDC00 + ((cp - 0x10000) & 0x3FF));
+            } else if (cp < 0x20 || cp >= 0x7F) {
+                snprintf(buf, sizeof(buf), "\\u%04X", cp);
+            } else {
+                buf[0] = cp;
+                buf[1] = 0;
+            }
+            qstring_append(qstring, buf);
+        }
+    };
+
+    qstring_append(qstring, "\"");
+    return result;
+}
-- 
2.7.4