qdict: implement a qdict_crumple method for un-flattening a dict

The qdict_flatten() method will take a dict whose elements are
further nested dicts/lists and flatten them by concatenating
keys.

The qdict_crumple() method aims to do the reverse, taking a flat
qdict, and turning it into a set of nested dicts/lists. It will
apply nesting based on the key name, with a '.' indicating a
new level in the hierarchy. If the keys in the nested structure
are all numeric, it will create a list, otherwise it will create
a dict.

If the keys are a mixture of numeric and non-numeric, or the
numeric keys are not in strictly ascending order, an error will
be reported.

As an example, a flat dict containing

 {
   'foo.0.bar': 'one',
   'foo.0.wizz': '1',
   'foo.1.bar': 'two',
   'foo.1.wizz': '2'
 }

will get turned into a dict with one element 'foo' whose
value is a list. The list elements will each in turn be
dicts.

 {
   'foo': [
     { 'bar': 'one', 'wizz': '1' },
     { 'bar': 'two', 'wizz': '2' }
   ],
 }

If the key is intended to contain a literal '.', then it must
be escaped as '..'. ie a flat dict

  {
     'foo..bar': 'wizz',
     'bar.foo..bar': 'eek',
     'bar.hello': 'world'
  }

Will end up as

  {
     'foo.bar': 'wizz',
     'bar': {
        'foo.bar': 'eek',
        'hello': 'world'
     }
  }

The intent of this function is that it allows a set of QemuOpts
to be turned into a nested data structure that mirrors the nesting
used when the same object is defined over QMP.

Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Signed-off-by: Daniel P. Berrange <berrange@redhat.com>
Message-Id: <1475246744-29302-3-git-send-email-berrange@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
[Parameter recursive dropped along with its tests; whitespace style
touched up]
Signed-off-by: Markus Armbruster <armbru@redhat.com>

1 files changed, 277 insertions, 0 deletions

diff --git a/qobject/qdict.c b/qobject/qdict.c
index 60f158c..197b0fb 100644
--- a/qobject/qdict.c
+++ b/qobject/qdict.c
@@ -17,6 +17,7 @@
 #include "qapi/qmp/qbool.h"
 #include "qapi/qmp/qstring.h"
 #include "qapi/qmp/qobject.h"
+#include "qapi/error.h"
 #include "qemu/queue.h"
 #include "qemu-common.h"
 #include "qemu/cutils.h"
@@ -684,6 +685,282 @@ void qdict_array_split(QDict *src, QList **dst)
 }
 
 /**
+ * qdict_split_flat_key:
+ * @key: the key string to split
+ * @prefix: non-NULL pointer to hold extracted prefix
+ * @suffix: non-NULL pointer to remaining suffix
+ *
+ * Given a flattened key such as 'foo.0.bar', split it into two parts
+ * at the first '.' separator. Allows double dot ('..') to escape the
+ * normal separator.
+ *
+ * e.g.
+ *    'foo.0.bar' -> prefix='foo' and suffix='0.bar'
+ *    'foo..0.bar' -> prefix='foo.0' and suffix='bar'
+ *
+ * The '..' sequence will be unescaped in the returned 'prefix'
+ * string. The 'suffix' string will be left in escaped format, so it
+ * can be fed back into the qdict_split_flat_key() key as the input
+ * later.
+ *
+ * The caller is responsible for freeing the string returned in @prefix
+ * using g_free().
+ */
+static void qdict_split_flat_key(const char *key, char **prefix,
+                                 const char **suffix)
+{
+    const char *separator;
+    size_t i, j;
+
+    /* Find first '.' separator, but if there is a pair '..'
+     * that acts as an escape, so skip over '..' */
+    separator = NULL;
+    do {
+        if (separator) {
+            separator += 2;
+        } else {
+            separator = key;
+        }
+        separator = strchr(separator, '.');
+    } while (separator && separator[1] == '.');
+
+    if (separator) {
+        *prefix = g_strndup(key, separator - key);
+        *suffix = separator + 1;
+    } else {
+        *prefix = g_strdup(key);
+        *suffix = NULL;
+    }
+
+    /* Unescape the '..' sequence into '.' */
+    for (i = 0, j = 0; (*prefix)[i] != '\0'; i++, j++) {
+        if ((*prefix)[i] == '.') {
+            assert((*prefix)[i + 1] == '.');
+            i++;
+        }
+        (*prefix)[j] = (*prefix)[i];
+    }
+    (*prefix)[j] = '\0';
+}
+
+/**
+ * qdict_is_list:
+ * @maybe_list: dict to check if keys represent list elements.
+ *
+ * Determine whether all keys in @maybe_list are valid list elements.
+ * If @maybe_list is non-zero in length and all the keys look like
+ * valid list indexes, this will return 1. If @maybe_list is zero
+ * length or all keys are non-numeric then it will return 0 to indicate
+ * it is a normal qdict. If there is a mix of numeric and non-numeric
+ * keys, or the list indexes are non-contiguous, an error is reported.
+ *
+ * Returns: 1 if a valid list, 0 if a dict, -1 on error
+ */
+static int qdict_is_list(QDict *maybe_list, Error **errp)
+{
+    const QDictEntry *ent;
+    ssize_t len = 0;
+    ssize_t max = -1;
+    int is_list = -1;
+    int64_t val;
+
+    for (ent = qdict_first(maybe_list); ent != NULL;
+         ent = qdict_next(maybe_list, ent)) {
+
+        if (qemu_strtoll(ent->key, NULL, 10, &val) == 0) {
+            if (is_list == -1) {
+                is_list = 1;
+            } else if (!is_list) {
+                error_setg(errp,
+                           "Cannot mix list and non-list keys");
+                return -1;
+            }
+            len++;
+            if (val > max) {
+                max = val;
+            }
+        } else {
+            if (is_list == -1) {
+                is_list = 0;
+            } else if (is_list) {
+                error_setg(errp,
+                           "Cannot mix list and non-list keys");
+                return -1;
+            }
+        }
+    }
+
+    if (is_list == -1) {
+        assert(!qdict_size(maybe_list));
+        is_list = 0;
+    }
+
+    /* NB this isn't a perfect check - e.g. it won't catch
+     * a list containing '1', '+1', '01', '3', but that
+     * does not matter - we've still proved that the
+     * input is a list. It is up the caller to do a
+     * stricter check if desired */
+    if (len != (max + 1)) {
+        error_setg(errp, "List indices are not contiguous, "
+                   "saw %zd elements but %zd largest index",
+                   len, max);
+        return -1;
+    }
+
+    return is_list;
+}
+
+/**
+ * qdict_crumple:
+ * @src: the original flat dictionary (only scalar values) to crumple
+ *
+ * Takes a flat dictionary whose keys use '.' separator to indicate
+ * nesting, and values are scalars, and crumples it into a nested
+ * structure.
+ *
+ * To include a literal '.' in a key name, it must be escaped as '..'
+ *
+ * For example, an input of:
+ *
+ * { 'foo.0.bar': 'one', 'foo.0.wizz': '1',
+ *   'foo.1.bar': 'two', 'foo.1.wizz': '2' }
+ *
+ * will result in an output of:
+ *
+ * {
+ *   'foo': [
+ *      { 'bar': 'one', 'wizz': '1' },
+ *      { 'bar': 'two', 'wizz': '2' }
+ *   ],
+ * }
+ *
+ * The following scenarios in the input dict will result in an
+ * error being returned:
+ *
+ *  - Any values in @src are non-scalar types
+ *  - If keys in @src imply that a particular level is both a
+ *    list and a dict. e.g., "foo.0.bar" and "foo.eek.bar".
+ *  - If keys in @src imply that a particular level is a list,
+ *    but the indices are non-contiguous. e.g. "foo.0.bar" and
+ *    "foo.2.bar" without any "foo.1.bar" present.
+ *  - If keys in @src represent list indexes, but are not in
+ *    the "%zu" format. e.g. "foo.+0.bar"
+ *
+ * Returns: either a QDict or QList for the nested data structure, or NULL
+ * on error
+ */
+QObject *qdict_crumple(const QDict *src, Error **errp)
+{
+    const QDictEntry *ent;
+    QDict *two_level, *multi_level = NULL;
+    QObject *dst = NULL, *child;
+    size_t i;
+    char *prefix = NULL;
+    const char *suffix = NULL;
+    int is_list;
+
+    two_level = qdict_new();
+
+    /* Step 1: split our totally flat dict into a two level dict */
+    for (ent = qdict_first(src); ent != NULL; ent = qdict_next(src, ent)) {
+        if (qobject_type(ent->value) == QTYPE_QDICT ||
+            qobject_type(ent->value) == QTYPE_QLIST) {
+            error_setg(errp, "Value %s is not a scalar",
+                       ent->key);
+            goto error;
+        }
+
+        qdict_split_flat_key(ent->key, &prefix, &suffix);
+
+        child = qdict_get(two_level, prefix);
+        if (suffix) {
+            if (child) {
+                if (qobject_type(child) != QTYPE_QDICT) {
+                    error_setg(errp, "Key %s prefix is already set as a scalar",
+                               prefix);
+                    goto error;
+                }
+            } else {
+                child = QOBJECT(qdict_new());
+                qdict_put_obj(two_level, prefix, child);
+            }
+            qobject_incref(ent->value);
+            qdict_put_obj(qobject_to_qdict(child), suffix, ent->value);
+        } else {
+            if (child) {
+                error_setg(errp, "Key %s prefix is already set as a dict",
+                           prefix);
+                goto error;
+            }
+            qobject_incref(ent->value);
+            qdict_put_obj(two_level, prefix, ent->value);
+        }
+
+        g_free(prefix);
+        prefix = NULL;
+    }
+
+    /* Step 2: optionally process the two level dict recursively
+     * into a multi-level dict */
+    multi_level = qdict_new();
+    for (ent = qdict_first(two_level); ent != NULL;
+         ent = qdict_next(two_level, ent)) {
+
+        if (qobject_type(ent->value) == QTYPE_QDICT) {
+            child = qdict_crumple(qobject_to_qdict(ent->value), errp);
+            if (!child) {
+                goto error;
+            }
+
+            qdict_put_obj(multi_level, ent->key, child);
+        } else {
+            qobject_incref(ent->value);
+            qdict_put_obj(multi_level, ent->key, ent->value);
+        }
+    }
+    QDECREF(two_level);
+    two_level = NULL;
+
+    /* Step 3: detect if we need to turn our dict into list */
+    is_list = qdict_is_list(multi_level, errp);
+    if (is_list < 0) {
+        goto error;
+    }
+
+    if (is_list) {
+        dst = QOBJECT(qlist_new());
+
+        for (i = 0; i < qdict_size(multi_level); i++) {
+            char *key = g_strdup_printf("%zu", i);
+
+            child = qdict_get(multi_level, key);
+            g_free(key);
+
+            if (!child) {
+                error_setg(errp, "Missing list index %zu", i);
+                goto error;
+            }
+
+            qobject_incref(child);
+            qlist_append_obj(qobject_to_qlist(dst), child);
+        }
+        QDECREF(multi_level);
+        multi_level = NULL;
+    } else {
+        dst = QOBJECT(multi_level);
+    }
+
+    return dst;
+
+ error:
+    g_free(prefix);
+    QDECREF(multi_level);
+    QDECREF(two_level);
+    qobject_decref(dst);
+    return NULL;
+}
+
+/**
  * qdict_array_entries(): Returns the number of direct array entries if the
  * sub-QDict of src specified by the prefix in subqdict (or src itself for
  * prefix == "") is valid as an array, i.e. the length of the created list if