Read JSON messages in message-json.c, for requests and answers alike

The in-place JSON reader of pure-serve's request bodies moves into its
own file with a small interface (pure_json_message, pure_json_fixed,
pure_json_space), so the delivery client can read an API's answers
with it. It gains a lenient mode for answers: a member that names no
field is skipped, value and all. Requests read as before.

1 files changed, 281 insertions, 0 deletions

diff --git a/prototypes/connections/message-json.c b/prototypes/connections/message-json.c
new file mode 100644
index 0000000..66c812d
--- /dev/null
+++ b/prototypes/connections/message-json.c
@@ -0,0 +1,281 @@
+#include "message-json.h"
+#include "module-text.h"
+#include <math.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+static void write_u32(unsigned char *p, uint32_t v) { for (unsigned i = 0; i < 4; ++i) p[i] = (unsigned char)(v >> (8 * i)); }
+
+static bool decimal(const char *text, uint64_t maximum, uint64_t *value) {
+    if (!*text) return false;
+    uint64_t n = 0;
+    for (; *text; ++text) {
+        if (*text < '0' || *text > '9') return false;
+        unsigned digit = (unsigned)(*text - '0');
+        if (n > (maximum - digit) / 10) return false;
+        n = n * 10 + digit;
+    }
+    *value = n;
+    return true;
+}
+
+/* A JSON number's text: -?(0|[1-9][0-9]*)(.[0-9]+)?([eE][+-]?[0-9]+)?, its
+ * length (0 if there is none). An integer has neither part after it. */
+static size_t json_number(const unsigned char *p, size_t size, bool *integer) {
+    size_t i = 0;
+    *integer = true;
+    if (i < size && p[i] == '-') ++i;
+    if (i == size || p[i] < '0' || p[i] > '9') return 0;
+    if (p[i++] != '0') while (i < size && p[i] >= '0' && p[i] <= '9') ++i;
+    if (i < size && p[i] == '.') {
+        *integer = false;
+        if (++i == size || p[i] < '0' || p[i] > '9') return 0;
+        while (i < size && p[i] >= '0' && p[i] <= '9') ++i;
+    }
+    if (i < size && (p[i] == 'e' || p[i] == 'E')) {
+        *integer = false;
+        if (++i < size && (p[i] == '+' || p[i] == '-')) ++i;
+        if (i == size || p[i] < '0' || p[i] > '9') return 0;
+        while (i < size && p[i] >= '0' && p[i] <= '9') ++i;
+    }
+    return i;
+}
+
+/* A fixed field's value from its text (a query value or a JSON number) into
+ * the prefix: a u32 in range, or a finite number. */
+bool pure_json_fixed(const PureField *field, const unsigned char *text, size_t size, unsigned char *prefix) {
+    bool integer;
+    if (!size || json_number(text, size, &integer) != size || size > 40) return false;
+    char digits[48];
+    memcpy(digits, text, size);
+    digits[size] = 0;
+    if (field->type == PURE_FIELD_U32) {
+        uint64_t n;
+        if (!integer || !decimal(digits, UINT32_MAX, &n)) return false;
+        write_u32(prefix + field->offset, (uint32_t)n);
+        return true;
+    }
+    double value = strtod(digits, NULL);
+    if (!isfinite(value)) return false;
+    memcpy(prefix + field->offset, &value, 8);
+    return true;
+}
+
+/* A JSON string's contents (after its opening quote) up to the closing one:
+ * its length, or 0 when it does not close or holds a control byte. */
+static size_t json_string_end(const unsigned char *p, size_t size) {
+    for (size_t i = 0; i < size; ++i) {
+        /* Eight bytes at a time while none is a quote, a backslash or a control byte. */
+        const uint64_t ones = UINT64_C(0x0101010101010101), highs = UINT64_C(0x8080808080808080);
+        for (uint64_t w, q, s; size - i >= 8; i += 8) {
+            memcpy(&w, p + i, 8);
+            q = w ^ (ones * '"');
+            s = w ^ (ones * '\\');
+            if (((q - ones) & ~q & highs) | ((s - ones) & ~s & highs) | ((w - ones * 0x20) & ~w & highs)) break;
+        }
+        if (i == size) break;
+        if (p[i] == '"') return i + 1;
+        if (p[i] < 0x20) return 0;
+        if (p[i] == '\\' && ++i == size) return 0;
+    }
+    return 0;
+}
+
+static int hex_digit(unsigned char c) {
+    return c >= '0' && c <= '9' ? c - '0' : c >= 'a' && c <= 'f' ? c - 'a' + 10 : c >= 'A' && c <= 'F' ? c - 'A' + 10 : -1;
+}
+
+static bool json_code(const unsigned char *p, size_t left, uint32_t *code) {
+    if (left < 4) return false;
+    *code = 0;
+    for (int i = 0; i < 4; ++i) {
+        int d = hex_digit(p[i]);
+        if (d < 0) return false;
+        *code = *code << 4 | (uint32_t)d;
+    }
+    return true;
+}
+
+/* Unescape a JSON string's contents into out (never longer); false for a
+ * bad escape or a lone surrogate. The result is checked as UTF-8 after. */
+static bool json_unescape(const unsigned char *in, size_t size, unsigned char *out, size_t *written) {
+    size_t o = 0;
+    for (size_t i = 0; i < size;) {
+        unsigned char b = in[i++];
+        if (b != '\\') { out[o++] = b; continue; }
+        if (i == size) return false;
+        b = in[i++];
+        const char *plain = strchr("\"\\/bfnrt", b);
+        if (b && plain) { out[o++] = (unsigned char)"\"\\/\b\f\n\r\t"[plain - "\"\\/bfnrt"]; continue; }
+        uint32_t code, low;
+        if (b != 'u' || !json_code(in + i, size - i, &code)) return false;
+        i += 4;
+        if (code >= 0xDC00 && code <= 0xDFFF) return false;
+        if (code >= 0xD800 && code <= 0xDBFF) {
+            if (size - i < 6 || in[i] != '\\' || in[i + 1] != 'u' || !json_code(in + i + 2, size - i - 2, &low) ||
+                low < 0xDC00 || low > 0xDFFF) return false;
+            i += 6;
+            code = 0x10000 + ((code - 0xD800) << 10) + (low - 0xDC00);
+        }
+        if (code < 0x80) out[o++] = (unsigned char)code;
+        else if (code < 0x800) { out[o++] = (unsigned char)(0xC0 | code >> 6); out[o++] = (unsigned char)(0x80 | (code & 0x3F)); }
+        else if (code < 0x10000) {
+            out[o++] = (unsigned char)(0xE0 | code >> 12);
+            out[o++] = (unsigned char)(0x80 | (code >> 6 & 0x3F));
+            out[o++] = (unsigned char)(0x80 | (code & 0x3F));
+        } else {
+            out[o++] = (unsigned char)(0xF0 | code >> 18);
+            out[o++] = (unsigned char)(0x80 | (code >> 12 & 0x3F));
+            out[o++] = (unsigned char)(0x80 | (code >> 6 & 0x3F));
+            out[o++] = (unsigned char)(0x80 | (code & 0x3F));
+        }
+    }
+    *written = o;
+    return true;
+}
+
+size_t pure_json_space(const unsigned char *p, size_t at, size_t size) {
+    while (at < size && (p[at] == ' ' || p[at] == '\t' || p[at] == '\n' || p[at] == '\r')) ++at;
+    return at;
+}
+
+/* Skip any JSON value at json[*at] (at most 64 deep): a member of an
+ * answer that names no field. */
+static bool skip_value(const unsigned char *json, size_t size, size_t *at, unsigned depth) {
+    if (*at == size || depth > 64) return false;
+    unsigned char b = json[*at];
+    bool integer;
+    if (b == '"') {
+        size_t end = json_string_end(json + *at + 1, size - *at - 1);
+        if (!end) return false;
+        *at += 1 + end;
+        return true;
+    }
+    if (b == '{' || b == '[') {
+        unsigned char close = b == '{' ? '}' : ']';
+        *at = pure_json_space(json, *at + 1, size);
+        for (bool first = true; *at < size && json[*at] != close; first = false) {
+            if (!first) {
+                if (json[(*at)++] != ',') return false;
+                *at = pure_json_space(json, *at, size);
+            }
+            if (close == '}') {
+                size_t key_end = *at < size && json[*at] == '"' ? json_string_end(json + *at + 1, size - *at - 1) : 0;
+                if (!key_end) return false;
+                *at = pure_json_space(json, *at + 1 + key_end, size);
+                if (*at == size || json[(*at)++] != ':') return false;
+                *at = pure_json_space(json, *at, size);
+            }
+            if (!skip_value(json, size, at, depth + 1)) return false;
+            *at = pure_json_space(json, *at, size);
+        }
+        if (*at == size) return false;
+        ++*at;
+        return true;
+    }
+    static const char *const words[] = {"true", "false", "null"};
+    for (size_t w = 0; w < 3; ++w)
+        if (size - *at >= strlen(words[w]) && !memcmp(json + *at, words[w], strlen(words[w]))) {
+            *at += strlen(words[w]);
+            return true;
+        }
+    size_t length = json_number(json + *at, size - *at, &integer);
+    *at += length;
+    return length > 0;
+}
+
+/* The field named path.key (key alone at the top), or the field count when
+ * none is; group says whether fields are named inside it instead. */
+static uint32_t field_named(const PureJsonMessage *b, const char *path, size_t path_size, const unsigned char *key,
+                            size_t key_size, bool *group) {
+    const PureModule *m = b->module;
+    size_t size = path_size + !!path_size + key_size;
+    *group = false;
+    for (uint32_t f = 0; f < b->shape->field_count; ++f) {
+        const char *name = m->field[b->shape->field_start + f].name;
+        size_t length = strlen(name);
+        if (length < size || memcmp(name, path, path_size) || (path_size && name[path_size] != '.') ||
+            memcmp(name + path_size + !!path_size, key, key_size)) continue;
+        if (length == size) return f;
+        if (name[size] == '.') *group = true;
+    }
+    return b->shape->field_count;
+}
+
+/* An object's members from json[*at] (its opening brace), in the group named
+ * path: a field's value, or a group's object. Strings stay where they are
+ * (an escaped one is unescaped over itself, which never makes it longer).
+ * NULL, or the error to answer. */
+static const char *members(PureJsonMessage *b, unsigned char *json, size_t size, size_t *at, const char *path, size_t path_size,
+                           unsigned depth) {
+    const PureModule *m = b->module;
+    if (*at == size || json[(*at)++] != '{') return "json";
+    *at = pure_json_space(json, *at, size);
+    for (bool first = true; *at < size && json[*at] != '}'; first = false) {
+        if (!first) {
+            if (json[(*at)++] != ',') return "json";
+            *at = pure_json_space(json, *at, size);
+        }
+        size_t key_end = *at < size && json[*at] == '"' ? json_string_end(json + *at + 1, size - *at - 1) : 0;
+        if (!key_end) return "json";
+        const unsigned char *key = json + *at + 1;
+        size_t key_size = key_end - 1;
+        *at = pure_json_space(json, *at + 1 + key_end, size);
+        if (*at == size || json[(*at)++] != ':') return "json";
+        *at = pure_json_space(json, *at, size);
+        bool group;
+        uint32_t f = field_named(b, path, path_size, key, key_size, &group);
+        if (f == b->shape->field_count && !group && b->lenient) { /* not the app's: skipped */
+            if (!skip_value(json, size, at, depth)) return "json";
+            *at = pure_json_space(json, *at, size);
+            continue;
+        }
+        if (*at < size && json[*at] == '{') {
+            if (!group) return f < b->shape->field_count ? "json_type" : "json_field";
+            char inner[PURE_MODULE_NAME];
+            size_t inner_size = path_size + !!path_size + key_size;
+            memcpy(inner, path, path_size);
+            if (path_size) inner[path_size] = '.';
+            memcpy(inner + path_size + !!path_size, key, key_size);
+            const char *why = members(b, json, size, at, inner, inner_size, depth + 1);
+            if (why) return why;
+            *at = pure_json_space(json, *at, size);
+            continue;
+        }
+        if (f == b->shape->field_count) return group ? "json_type" : "json_field";
+        if (b->seen[f] || (b->given && b->given[f])) return "json_field";
+        b->seen[f] = true;
+        const PureField *field = &m->field[b->shape->field_start + f];
+        bool variable = field->type == PURE_FIELD_BYTES || field->type == PURE_FIELD_TEXT, integer;
+        if (*at < size && json[*at] == '"') {
+            size_t end = json_string_end(json + *at + 1, size - *at - 1), written;
+            if (!end) return "json";
+            if (!variable) return "json_type";
+            unsigned char *value = json + *at + 1;
+            if (!memchr(value, '\\', end - 1)) written = end - 1;
+            else if (!json_unescape(value, end - 1, value, &written)) return "json";
+            if (field->type == PURE_FIELD_TEXT && !pure_utf8_valid((PureSpan){value, written})) return "json";
+            write_u32(b->table + 8 * f, (uint32_t)(value - b->payload));
+            write_u32(b->table + 8 * f + 4, (uint32_t)written);
+            *at = pure_json_space(json, *at + 1 + end, size);
+            continue;
+        }
+        size_t length = json_number(json + *at, size - *at, &integer);
+        if (!length) {
+            static const char *const words[] = {"true", "false", "null"};
+            for (size_t w = 0; w < 3 && !length; ++w)
+                if (size - *at >= strlen(words[w]) && !memcmp(json + *at, words[w], strlen(words[w]))) return "json_type";
+            return *at < size && json[*at] == '[' ? "json_type" : "json";
+        }
+        if (variable || !pure_json_fixed(field, json + *at, length, b->payload)) return "json_type";
+        *at = pure_json_space(json, *at + length, size);
+    }
+    if (*at == size) return "json";
+    ++*at;
+    return NULL;
+}
+
+const char *pure_json_message(PureJsonMessage *message, unsigned char *json, size_t size, size_t *at) {
+    return members(message, json, size, at, "", 0, 0);
+}