Changeset: 15668d66195b for MonetDB
URL: https://dev.monetdb.org/hg/MonetDB/rev/15668d66195b
Modified Files:
monetdb5/modules/atoms/pg_jsonpath/jsonpath.h
monetdb5/modules/atoms/pg_jsonpath/jsonpath_internal.h
monetdb5/modules/atoms/pg_jsonpath/jsonpath_scan.l
monetdb5/modules/atoms/pg_jsonpath/postgres_defines_internal.h
Branch: json-extend
Log Message:
scanner jsonpath_scan compiles
diffs (230 lines):
diff --git a/monetdb5/modules/atoms/pg_jsonpath/jsonpath.h
b/monetdb5/modules/atoms/pg_jsonpath/jsonpath.h
--- a/monetdb5/modules/atoms/pg_jsonpath/jsonpath.h
+++ b/monetdb5/modules/atoms/pg_jsonpath/jsonpath.h
@@ -273,7 +273,7 @@ typedef struct JsonPathParseResult
bool lax;
} JsonPathParseResult;
-extern struct Node * init_escontext();
+extern struct Node * init_escontext(void);
extern JsonPathParseResult *parsejsonpath(const char *str, int len,
struct Node *escontext);
diff --git a/monetdb5/modules/atoms/pg_jsonpath/jsonpath_internal.h
b/monetdb5/modules/atoms/pg_jsonpath/jsonpath_internal.h
--- a/monetdb5/modules/atoms/pg_jsonpath/jsonpath_internal.h
+++ b/monetdb5/modules/atoms/pg_jsonpath/jsonpath_internal.h
@@ -27,6 +27,7 @@ typedef struct JsonPathString
#include "postgres_defines_internal.h"
#include "jsonpath_gram.h"
+#define YY_USER_INIT (void) result;
#define YY_DECL extern int jsonpath_yylex(YYSTYPE *yylval_param, \
JsonPathParseResult
**result, \
struct Node
*escontext)
diff --git a/monetdb5/modules/atoms/pg_jsonpath/jsonpath_scan.l
b/monetdb5/modules/atoms/pg_jsonpath/jsonpath_scan.l
--- a/monetdb5/modules/atoms/pg_jsonpath/jsonpath_scan.l
+++ b/monetdb5/modules/atoms/pg_jsonpath/jsonpath_scan.l
@@ -428,7 +428,7 @@ static const JsonPathKeyword keywords[]
/* Check if current scanstring value is a keyword */
static enum yytokentype
-checkKeyword()
+checkKeyword(void)
{
int res = IDENT_P;
int diff;
@@ -552,9 +552,9 @@ addchar(bool init, char c)
/* initial jsonpath parser context */
struct Node *
-init_escontext()
+init_escontext(void)
{
- struct Node * escontext = GDKmalloc(struct Node);
+ struct Node * escontext = GDKmalloc(sizeof(struct Node));
if (!escontext)
return NULL;
@@ -624,13 +624,8 @@ addUnicodeChar(int ch, struct Node *esco
* conversion function. Otherwise call the normal form which
provides
* more detailed errors.
*/
-
- if (! escontext || ! IsA(escontext, ErrorSaveContext))
- pg_unicode_to_server(ch, (unsigned char *) cbuf);
- else if (!pg_unicode_to_server_noerror(ch, (unsigned char *)
cbuf))
- ereturn(escontext, false,
- (errcode(ERRCODE_SYNTAX_ERROR),
- errmsg("could not convert Unicode to
server encoding")));
+ if (!pg_unicode_to_server_noerror(ch, (unsigned char *) cbuf))
+ ereturn(escontext, "could not convert Unicode to server
encoding");
addstring(false, cbuf, strlen(cbuf));
}
return true;
diff --git a/monetdb5/modules/atoms/pg_jsonpath/postgres_defines_internal.h
b/monetdb5/modules/atoms/pg_jsonpath/postgres_defines_internal.h
--- a/monetdb5/modules/atoms/pg_jsonpath/postgres_defines_internal.h
+++ b/monetdb5/modules/atoms/pg_jsonpath/postgres_defines_internal.h
@@ -24,20 +24,26 @@ typedef struct StringInfoData
typedef StringInfoData *StringInfo;
-struct Node {
+
+typedef struct Node
+{
allocator *sa;
-};
+} Node;
#define SOFT_ERROR_OCCURRED(escontext) (false)
#define TODO_ERROR 0
-#define ereturn(context, dummy_value, ...) return TODO_ERROR;
+#define ereturn(context, dummy_value, ...) {(void) context; return
TODO_ERROR;}
#define errcode(X) /* TODO */
#define errmsg(X) /* TODO */
-#define palloc(X) GDKmalloc(X)
+#define palloc(X) GDKmalloc(X)
+#define pfree(X) GDKfree(X)
+#define repalloc(M,NSIZE) GDKrealloc(M, NSIZE)
+
+#define Max(A,B) MAX(A, B)
#define SA (escontext->sa)
#define list_make1(X) sa_list_append(SA, NULL, X)
@@ -84,4 +90,132 @@ for (;cell;cell = cell->next)
#define NIL NULL
#define PG_UINT32_MAX ((uint32) UINT32_MAX)
+#define ereport(c, m) (void) fmt; (void) msg;
+#define ERROR "TODO"
+#define errmsg_internal(frmt, msg) "TODO"
+
+#define errsave(a,b) (void) result; (void) escontext; (void) message;
+
+// c.h
+#define lengthof(array) (sizeof (array) / sizeof ((array)[0]))
+
+#define pg_strncasecmp(s1, s2, l2) GDKstrncasecmp(s1, s2, strlen(s1), l2)
+
+// pg_wchar.h
+#define MAX_UNICODE_EQUIVALENT_STRING 16
+#define MAX_MULTIBYTE_CHAR_LEN 4
+
+// pg_wchar.h
+typedef unsigned int pg_wchar;
+
+// pg_wchar.h
+static inline bool
+is_valid_unicode_codepoint(pg_wchar c)
+{
+ return (c > 0 && c <= 0x10FFFF);
+}
+
+// pg_wchar.h
+static inline bool
+is_utf16_surrogate_first(pg_wchar c)
+{
+ return (c >= 0xD800 && c <= 0xDBFF);
+}
+
+// pg_wchar.h
+static inline bool
+is_utf16_surrogate_second(pg_wchar c)
+{
+ return (c >= 0xDC00 && c <= 0xDFFF);
+}
+
+// pg_wchar.h
+static inline pg_wchar
+surrogate_pair_to_codepoint(pg_wchar first, pg_wchar second)
+{
+ return ((first & 0x3FF) << 10) + 0x10000 + (second & 0x3FF);
+}
+
+// pg_wchar.h
+static inline
+int
+pg_utf_mblen(const unsigned char *s)
+{
+ int len;
+
+ if ((*s & 0x80) == 0)
+ len = 1;
+ else if ((*s & 0xe0) == 0xc0)
+ len = 2;
+ else if ((*s & 0xf0) == 0xe0)
+ len = 3;
+ else if ((*s & 0xf8) == 0xf0)
+ len = 4;
+#ifdef NOT_USED
+ else if ((*s & 0xfc) == 0xf8)
+ len = 5;
+ else if ((*s & 0xfe) == 0xfc)
+ len = 6;
#endif
+ else
+ len = 1;
+ return len;
+}
+
+// pg_wchar.h
+static inline unsigned char *
+unicode_to_utf8(pg_wchar c, unsigned char *utf8string)
+{
+ if (c <= 0x7F)
+ {
+ utf8string[0] = c;
+ }
+ else if (c <= 0x7FF)
+ {
+ utf8string[0] = 0xC0 | ((c >> 6) & 0x1F);
+ utf8string[1] = 0x80 | (c & 0x3F);
+ }
+ else if (c <= 0xFFFF)
+ {
+ utf8string[0] = 0xE0 | ((c >> 12) & 0x0F);
+ utf8string[1] = 0x80 | ((c >> 6) & 0x3F);
+ utf8string[2] = 0x80 | (c & 0x3F);
+ }
+ else
+ {
+ utf8string[0] = 0xF0 | ((c >> 18) & 0x07);
+ utf8string[1] = 0x80 | ((c >> 12) & 0x3F);
+ utf8string[2] = 0x80 | ((c >> 6) & 0x3F);
+ utf8string[3] = 0x80 | (c & 0x3F);
+ }
+
+ return utf8string;
+}
+
+// mbutils.h
+static inline
+bool
+pg_unicode_to_server_noerror(pg_wchar c, unsigned char *s)
+{
+ /*
+ * Complain if invalid Unicode code point. The choice of errcode here
is
+ * debatable, but really our caller should have checked this anyway.
+ */
+ if (!is_valid_unicode_codepoint(c))
+ return false;
+
+ /* Otherwise, if it's in ASCII range, conversion is trivial */
+ if (c <= 0x7F)
+ {
+ s[0] = (unsigned char) c;
+ s[1] = '\0';
+ return true;
+ }
+
+ /* If the server encoding is UTF-8, we just need to reformat the code */
+ unicode_to_utf8(c, s);
+ s[pg_utf_mblen(s)] = '\0';
+ return true;
+}
+
+#endif
_______________________________________________
checkin-list mailing list -- [email protected]
To unsubscribe send an email to [email protected]
