From 58b7d95a7ec9c576f8a06bbab07f755846b5349a Mon Sep 17 00:00:00 2001
From: thiagoftsm <49162938+thiagoftsm@users.noreply.github.com>
Date: Thu, 6 Jun 2019 17:01:39 +0000
Subject: New URL parser (#6070)

* URL_parser 3

* URL_parser rebase 2!

* URL_parameter parsing 3

* URL_parameter parsing 4

* URL_parameter parsing 5

* URL_parser alarms

* URL_parser finish the basic structure

* URL_parser codacity fixes!

* URL_parser scripts!

* URL_parser codacy!

* URL_parser rebase 3!

* URL_parser host fixes!

* URL_parser host fixes 2!

* URL_parser fix spaces!

* URL_parser error message!

* URL_parser Christopher requests!

* URL_parser alarms fixed!

* URL_parser health fixed!

* URL_parser rebase 4!

* URL_parser C fix write format!

* URL_parser fix bugs due cache!
---
 libnetdata/inlined.h | 28 +++++++++++++++++
 libnetdata/url/url.c | 85 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 libnetdata/url/url.h | 22 ++++++++++++++
 3 files changed, 135 insertions(+)

(limited to 'libnetdata')

diff --git a/libnetdata/inlined.h b/libnetdata/inlined.h
index 6a5994c12a..a9c3e472e4 100644
--- a/libnetdata/inlined.h
+++ b/libnetdata/inlined.h
@@ -31,6 +31,19 @@ static inline uint32_t simple_hash(const char *name) {
     return hval;
 }
 
+static inline uint32_t simple_nhash(const char *name,size_t len) {
+    unsigned char *s = (unsigned char *) name;
+    size_t i;
+    uint32_t hval = 0x811c9dc5;
+    i = 0;
+    do {
+        hval *= 16777619;
+        hval ^= (uint32_t) *s++;
+    } while (++i < len);
+
+    return hval;
+}
+
 static inline uint32_t simple_uhash(const char *name) {
     unsigned char *s = (unsigned char *) name;
     uint32_t hval = 0x811c9dc5, c;
@@ -42,6 +55,21 @@ static inline uint32_t simple_uhash(const char *name) {
     return hval;
 }
 
+static inline uint32_t simple_nuhash(const char *name,size_t len) {
+    unsigned char *s = (unsigned char *) name;
+    size_t i;
+    uint32_t hval = 0x811c9dc5, c;
+
+    i = 0;
+    do {
+        c = *s++;
+        if (unlikely(c >= 'A' && c <= 'Z')) c += 'a' - 'A';
+        hval *= 16777619;
+        hval ^= c;
+    } while ( ++i < len);
+    return hval;
+}
+
 static inline int simple_hash_strcmp(const char *name, const char *b, uint32_t *hash) {
     unsigned char *s = (unsigned char *) name;
     uint32_t hval = 0x811c9dc5;
diff --git a/libnetdata/url/url.c b/libnetdata/url/url.c
index 07a9f8069e..fb1fb7f07a 100644
--- a/libnetdata/url/url.c
+++ b/libnetdata/url/url.c
@@ -79,3 +79,88 @@ char *url_decode_r(char *to, char *url, size_t size) {
 
     return to;
 }
+
+inline HTTP_VALIDATION url_is_request_complete(char *begin,char *end,size_t length) {
+    if ( begin == end) {
+        return HTTP_VALIDATION_INCOMPLETE;
+    }
+
+    if ( length > 3  ) {
+        begin = end - 4;
+    }
+
+    uint32_t counter = 0;
+    do {
+        if (*begin == '\r') {
+            begin++;
+            if ( begin == end )
+            {
+                break;
+            }
+
+            if (*begin == '\n')
+            {
+                counter++;
+            }
+        } else if (*begin == '\n') {
+            begin++;
+            counter++;
+        }
+
+        if ( counter == 2) {
+            break;
+        }
+    }
+    while (begin != end);
+
+    return (counter == 2)?HTTP_VALIDATION_OK:HTTP_VALIDATION_INCOMPLETE;
+}
+
+inline char *url_find_protocol(char *s) {
+    while(*s) {
+        // find the next space
+        while (*s && *s != ' ') s++;
+
+        // is it SPACE + "HTTP/" ?
+        if(*s && !strncmp(s, " HTTP/", 6)) break;
+        else s++;
+    }
+
+    return s;
+}
+
+int url_parse_query_string(struct web_fields *names,struct web_fields *values,char *moveme,char *divisor) {
+    uint32_t i = 0;
+    uint32_t max = WEB_FIELDS_MAX;
+
+    do {
+        if ( i == max) {
+            error("We are exceeding the maximum number of elements possible(%u) in this query string(%s)",max,moveme);
+            break;
+        }
+        if (divisor) {
+            names[i].body = moveme;
+            names[i].length = divisor - moveme;//= - begin
+
+            moveme = ++divisor; //value
+            values[i].body = moveme;
+
+            (void)divisor;
+            divisor = strchr(moveme,'&'); //end of value
+            if (divisor) {
+                values[i].length = (size_t )(divisor - moveme);
+            } else{
+                values[i].length = strlen(moveme);
+                break;
+            }
+
+            moveme = divisor;
+            divisor = strchr(++moveme,'='); //end of value
+            i++;
+        } else {
+            break;
+        }
+    } while (moveme);
+
+    return ++i;
+}
diff --git a/libnetdata/url/url.h b/libnetdata/url/url.h
index 6cef6d7a84..9e86c20cfd 100644
--- a/libnetdata/url/url.h
+++ b/libnetdata/url/url.h
@@ -25,4 +25,26 @@ extern char *url_decode(char *str);
 
 extern char *url_decode_r(char *to, char *url, size_t size);
 
+#define WEB_FIELDS_MAX 200
+struct web_fields{
+    char *body;
+    size_t length;
+};
+// http_request_validate()
+// returns:
+// = 0 : all good, process the request
+// > 0 : request is not supported
+// < 0 : request is incomplete - wait for more data
+
+typedef enum {
+    HTTP_VALIDATION_OK,
+    HTTP_VALIDATION_NOT_SUPPORTED,
+    HTTP_VALIDATION_INCOMPLETE,
+    HTTP_VALIDATION_REDIRECT
+} HTTP_VALIDATION;
+
+extern HTTP_VALIDATION url_is_request_complete(char *begin,char *end,size_t length);
+extern char *url_find_protocol(char *s);
+extern int url_parse_query_string(struct web_fields *names,struct web_fields *values,char *moveme,char *divisor);
+
 #endif /* NETDATA_URL_H */
-- 
cgit v1.2.3