pg_query 1.3.0 → 2.0.0

data/ext/pg_query/src_common_kwlookup.c

@@ -0,0 +1,91 @@
+/*--------------------------------------------------------------------
+ * Symbols referenced in this file:
+ * - ScanKeywordLookup
+ *--------------------------------------------------------------------
+ */
+
+/*-------------------------------------------------------------------------
+ *
+ * kwlookup.c
+ *	  Key word lookup for PostgreSQL
+ *
+ *
+ * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ *
+ * IDENTIFICATION
+ *	  src/common/kwlookup.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#include "common/kwlookup.h"
+
+
+/*
+ * ScanKeywordLookup - see if a given word is a keyword
+ *
+ * The list of keywords to be matched against is passed as a ScanKeywordList.
+ *
+ * Returns the keyword number (0..N-1) of the keyword, or -1 if no match.
+ * Callers typically use the keyword number to index into information
+ * arrays, but that is no concern of this code.
+ *
+ * The match is done case-insensitively.  Note that we deliberately use a
+ * dumbed-down case conversion that will only translate 'A'-'Z' into 'a'-'z',
+ * even if we are in a locale where tolower() would produce more or different
+ * translations.  This is to conform to the SQL99 spec, which says that
+ * keywords are to be matched in this way even though non-keyword identifiers
+ * receive a different case-normalization mapping.
+ */
+int
+ScanKeywordLookup(const char *str,
+				  const ScanKeywordList *keywords)
+{
+	size_t		len;
+	int			h;
+	const char *kw;
+
+	/*
+	 * Reject immediately if too long to be any keyword.  This saves useless
+	 * hashing and downcasing work on long strings.
+	 */
+	len = strlen(str);
+	if (len > keywords->max_kw_len)
+		return -1;
+
+	/*
+	 * Compute the hash function.  We assume it was generated to produce
+	 * case-insensitive results.  Since it's a perfect hash, we need only
+	 * match to the specific keyword it identifies.
+	 */
+	h = keywords->hash(str, len);
+
+	/* An out-of-range result implies no match */
+	if (h < 0 || h >= keywords->num_keywords)
+		return -1;
+
+	/*
+	 * Compare character-by-character to see if we have a match, applying an
+	 * ASCII-only downcasing to the input characters.  We must not use
+	 * tolower() since it may produce the wrong translation in some locales
+	 * (eg, Turkish).
+	 */
+	kw = GetScanKeyword(h, keywords);
+	while (*str != '\0')
+	{
+		char		ch = *str++;
+
+		if (ch >= 'A' && ch <= 'Z')
+			ch += 'a' - 'A';
+		if (ch != *kw++)
+			return -1;
+	}
+	if (*kw != '\0')
+		return -1;
+
+	/* Success! */
+	return h;
+}

data/ext/pg_query/src_common_psprintf.c

@@ -0,0 +1,158 @@
+/*--------------------------------------------------------------------
+ * Symbols referenced in this file:
+ * - pvsnprintf
+ * - psprintf
+ *--------------------------------------------------------------------
+ */
+
+/*-------------------------------------------------------------------------
+ *
+ * psprintf.c
+ *		sprintf into an allocated-on-demand buffer
+ *
+ *
+ * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ *
+ * IDENTIFICATION
+ *	  src/common/psprintf.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef FRONTEND
+
+#include "postgres.h"
+
+#include "utils/memutils.h"
+
+#else
+
+#include "postgres_fe.h"
+
+/* It's possible we could use a different value for this in frontend code */
+#define MaxAllocSize	((Size) 0x3fffffff) /* 1 gigabyte - 1 */
+
+#endif
+
+
+/*
+ * psprintf
+ *
+ * Format text data under the control of fmt (an sprintf-style format string)
+ * and return it in an allocated-on-demand buffer.  The buffer is allocated
+ * with palloc in the backend, or malloc in frontend builds.  Caller is
+ * responsible to free the buffer when no longer needed, if appropriate.
+ *
+ * Errors are not returned to the caller, but are reported via elog(ERROR)
+ * in the backend, or printf-to-stderr-and-exit() in frontend builds.
+ * One should therefore think twice about using this in libpq.
+ */
+char *
+psprintf(const char *fmt,...)
+{
+	int			save_errno = errno;
+	size_t		len = 128;		/* initial assumption about buffer size */
+
+	for (;;)
+	{
+		char	   *result;
+		va_list		args;
+		size_t		newlen;
+
+		/*
+		 * Allocate result buffer.  Note that in frontend this maps to malloc
+		 * with exit-on-error.
+		 */
+		result = (char *) palloc(len);
+
+		/* Try to format the data. */
+		errno = save_errno;
+		va_start(args, fmt);
+		newlen = pvsnprintf(result, len, fmt, args);
+		va_end(args);
+
+		if (newlen < len)
+			return result;		/* success */
+
+		/* Release buffer and loop around to try again with larger len. */
+		pfree(result);
+		len = newlen;
+	}
+}
+
+/*
+ * pvsnprintf
+ *
+ * Attempt to format text data under the control of fmt (an sprintf-style
+ * format string) and insert it into buf (which has length len).
+ *
+ * If successful, return the number of bytes emitted, not counting the
+ * trailing zero byte.  This will always be strictly less than len.
+ *
+ * If there's not enough space in buf, return an estimate of the buffer size
+ * needed to succeed (this *must* be more than the given len, else callers
+ * might loop infinitely).
+ *
+ * Other error cases do not return, but exit via elog(ERROR) or exit().
+ * Hence, this shouldn't be used inside libpq.
+ *
+ * Caution: callers must be sure to preserve their entry-time errno
+ * when looping, in case the fmt contains "%m".
+ *
+ * Note that the semantics of the return value are not exactly C99's.
+ * First, we don't promise that the estimated buffer size is exactly right;
+ * callers must be prepared to loop multiple times to get the right size.
+ * (Given a C99-compliant vsnprintf, that won't happen, but it is rumored
+ * that some implementations don't always return the same value ...)
+ * Second, we return the recommended buffer size, not one less than that;
+ * this lets overflow concerns be handled here rather than in the callers.
+ */
+size_t
+pvsnprintf(char *buf, size_t len, const char *fmt, va_list args)
+{
+	int			nprinted;
+
+	nprinted = vsnprintf(buf, len, fmt, args);
+
+	/* We assume failure means the fmt is bogus, hence hard failure is OK */
+	if (unlikely(nprinted < 0))
+	{
+#ifndef FRONTEND
+		elog(ERROR, "vsnprintf failed: %m with format string \"%s\"", fmt);
+#else
+		fprintf(stderr, "vsnprintf failed: %s with format string \"%s\"\n",
+				strerror(errno), fmt);
+		exit(EXIT_FAILURE);
+#endif
+	}
+
+	if ((size_t) nprinted < len)
+	{
+		/* Success.  Note nprinted does not include trailing null. */
+		return (size_t) nprinted;
+	}
+
+	/*
+	 * We assume a C99-compliant vsnprintf, so believe its estimate of the
+	 * required space, and add one for the trailing null.  (If it's wrong, the
+	 * logic will still work, but we may loop multiple times.)
+	 *
+	 * Choke if the required space would exceed MaxAllocSize.  Note we use
+	 * this palloc-oriented overflow limit even when in frontend.
+	 */
+	if (unlikely((size_t) nprinted > MaxAllocSize - 1))
+	{
+#ifndef FRONTEND
+		ereport(ERROR,
+				(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
+				 errmsg("out of memory")));
+#else
+		fprintf(stderr, _("out of memory\n"));
+		exit(EXIT_FAILURE);
+#endif
+	}
+
+	return nprinted + 1;
+}

data/ext/pg_query/src_common_string.c

@@ -0,0 +1,86 @@
+/*--------------------------------------------------------------------
+ * Symbols referenced in this file:
+ * - strtoint
+ *--------------------------------------------------------------------
+ */
+
+/*-------------------------------------------------------------------------
+ *
+ * string.c
+ *		string handling helpers
+ *
+ *
+ * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ *
+ * IDENTIFICATION
+ *	  src/common/string.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+
+#ifndef FRONTEND
+#include "postgres.h"
+#else
+#include "postgres_fe.h"
+#endif
+
+#include "common/string.h"
+
+
+/*
+ * Returns whether the string `str' has the postfix `end'.
+ */
+
+
+
+/*
+ * strtoint --- just like strtol, but returns int not long
+ */
+int
+strtoint(const char *pg_restrict str, char **pg_restrict endptr, int base)
+{
+	long		val;
+
+	val = strtol(str, endptr, base);
+	if (val != (int) val)
+		errno = ERANGE;
+	return (int) val;
+}
+
+
+/*
+ * pg_clean_ascii -- Replace any non-ASCII chars with a '?' char
+ *
+ * Modifies the string passed in which must be '\0'-terminated.
+ *
+ * This function exists specifically to deal with filtering out
+ * non-ASCII characters in a few places where the client can provide an almost
+ * arbitrary string (and it isn't checked to ensure it's a valid username or
+ * database name or similar) and we don't want to have control characters or other
+ * things ending up in the log file where server admins might end up with a
+ * messed up terminal when looking at them.
+ *
+ * In general, this function should NOT be used- instead, consider how to handle
+ * the string without needing to filter out the non-ASCII characters.
+ *
+ * Ultimately, we'd like to improve the situation to not require stripping out
+ * all non-ASCII but perform more intelligent filtering which would allow UTF or
+ * similar, but it's unclear exactly what we should allow, so stick to ASCII only
+ * for now.
+ */
+
+
+
+/*
+ * pg_strip_crlf -- Remove any trailing newline and carriage return
+ *
+ * Removes any trailing newline and carriage return characters (\r on
+ * Windows) in the input string, zero-terminating it.
+ *
+ * The passed in string must be zero-terminated.  This function returns
+ * the new length of the string.
+ */
+

data/ext/pg_query/src_common_stringinfo.c

@@ -0,0 +1,336 @@
+/*--------------------------------------------------------------------
+ * Symbols referenced in this file:
+ * - initStringInfo
+ * - resetStringInfo
+ * - appendStringInfoString
+ * - appendBinaryStringInfo
+ * - appendStringInfoChar
+ * - appendStringInfoVA
+ * - enlargeStringInfo
+ * - appendStringInfo
+ * - appendStringInfoSpaces
+ *--------------------------------------------------------------------
+ */
+
+/*-------------------------------------------------------------------------
+ *
+ * stringinfo.c
+ *
+ * StringInfo provides an extensible string data type (currently limited to a
+ * length of 1GB).  It can be used to buffer either ordinary C strings
+ * (null-terminated text) or arbitrary binary data.  All storage is allocated
+ * with palloc() (falling back to malloc in frontend code).
+ *
+ * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ *	  src/common/stringinfo.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef FRONTEND
+
+#include "postgres.h"
+#include "utils/memutils.h"
+
+#else
+
+#include "postgres_fe.h"
+
+/* It's possible we could use a different value for this in frontend code */
+#define MaxAllocSize	((Size) 0x3fffffff) /* 1 gigabyte - 1 */
+
+#endif
+
+#include "lib/stringinfo.h"
+
+
+/*
+ * makeStringInfo
+ *
+ * Create an empty 'StringInfoData' & return a pointer to it.
+ */
+
+
+/*
+ * initStringInfo
+ *
+ * Initialize a StringInfoData struct (with previously undefined contents)
+ * to describe an empty string.
+ */
+void
+initStringInfo(StringInfo str)
+{
+	int			size = 1024;	/* initial default buffer size */
+
+	str->data = (char *) palloc(size);
+	str->maxlen = size;
+	resetStringInfo(str);
+}
+
+/*
+ * resetStringInfo
+ *
+ * Reset the StringInfo: the data buffer remains valid, but its
+ * previous content, if any, is cleared.
+ */
+void
+resetStringInfo(StringInfo str)
+{
+	str->data[0] = '\0';
+	str->len = 0;
+	str->cursor = 0;
+}
+
+/*
+ * appendStringInfo
+ *
+ * Format text data under the control of fmt (an sprintf-style format string)
+ * and append it to whatever is already in str.  More space is allocated
+ * to str if necessary.  This is sort of like a combination of sprintf and
+ * strcat.
+ */
+void
+appendStringInfo(StringInfo str, const char *fmt,...)
+{
+	int			save_errno = errno;
+
+	for (;;)
+	{
+		va_list		args;
+		int			needed;
+
+		/* Try to format the data. */
+		errno = save_errno;
+		va_start(args, fmt);
+		needed = appendStringInfoVA(str, fmt, args);
+		va_end(args);
+
+		if (needed == 0)
+			break;				/* success */
+
+		/* Increase the buffer size and try again. */
+		enlargeStringInfo(str, needed);
+	}
+}
+
+/*
+ * appendStringInfoVA
+ *
+ * Attempt to format text data under the control of fmt (an sprintf-style
+ * format string) and append it to whatever is already in str.  If successful
+ * return zero; if not (because there's not enough space), return an estimate
+ * of the space needed, without modifying str.  Typically the caller should
+ * pass the return value to enlargeStringInfo() before trying again; see
+ * appendStringInfo for standard usage pattern.
+ *
+ * Caution: callers must be sure to preserve their entry-time errno
+ * when looping, in case the fmt contains "%m".
+ *
+ * XXX This API is ugly, but there seems no alternative given the C spec's
+ * restrictions on what can portably be done with va_list arguments: you have
+ * to redo va_start before you can rescan the argument list, and we can't do
+ * that from here.
+ */
+int
+appendStringInfoVA(StringInfo str, const char *fmt, va_list args)
+{
+	int			avail;
+	size_t		nprinted;
+
+	Assert(str != NULL);
+
+	/*
+	 * If there's hardly any space, don't bother trying, just fail to make the
+	 * caller enlarge the buffer first.  We have to guess at how much to
+	 * enlarge, since we're skipping the formatting work.
+	 */
+	avail = str->maxlen - str->len;
+	if (avail < 16)
+		return 32;
+
+	nprinted = pvsnprintf(str->data + str->len, (size_t) avail, fmt, args);
+
+	if (nprinted < (size_t) avail)
+	{
+		/* Success.  Note nprinted does not include trailing null. */
+		str->len += (int) nprinted;
+		return 0;
+	}
+
+	/* Restore the trailing null so that str is unmodified. */
+	str->data[str->len] = '\0';
+
+	/*
+	 * Return pvsnprintf's estimate of the space needed.  (Although this is
+	 * given as a size_t, we know it will fit in int because it's not more
+	 * than MaxAllocSize.)
+	 */
+	return (int) nprinted;
+}
+
+/*
+ * appendStringInfoString
+ *
+ * Append a null-terminated string to str.
+ * Like appendStringInfo(str, "%s", s) but faster.
+ */
+void
+appendStringInfoString(StringInfo str, const char *s)
+{
+	appendBinaryStringInfo(str, s, strlen(s));
+}
+
+/*
+ * appendStringInfoChar
+ *
+ * Append a single byte to str.
+ * Like appendStringInfo(str, "%c", ch) but much faster.
+ */
+void
+appendStringInfoChar(StringInfo str, char ch)
+{
+	/* Make more room if needed */
+	if (str->len + 1 >= str->maxlen)
+		enlargeStringInfo(str, 1);
+
+	/* OK, append the character */
+	str->data[str->len] = ch;
+	str->len++;
+	str->data[str->len] = '\0';
+}
+
+/*
+ * appendStringInfoSpaces
+ *
+ * Append the specified number of spaces to a buffer.
+ */
+void
+appendStringInfoSpaces(StringInfo str, int count)
+{
+	if (count > 0)
+	{
+		/* Make more room if needed */
+		enlargeStringInfo(str, count);
+
+		/* OK, append the spaces */
+		while (--count >= 0)
+			str->data[str->len++] = ' ';
+		str->data[str->len] = '\0';
+	}
+}
+
+/*
+ * appendBinaryStringInfo
+ *
+ * Append arbitrary binary data to a StringInfo, allocating more space
+ * if necessary. Ensures that a trailing null byte is present.
+ */
+void
+appendBinaryStringInfo(StringInfo str, const char *data, int datalen)
+{
+	Assert(str != NULL);
+
+	/* Make more room if needed */
+	enlargeStringInfo(str, datalen);
+
+	/* OK, append the data */
+	memcpy(str->data + str->len, data, datalen);
+	str->len += datalen;
+
+	/*
+	 * Keep a trailing null in place, even though it's probably useless for
+	 * binary data.  (Some callers are dealing with text but call this because
+	 * their input isn't null-terminated.)
+	 */
+	str->data[str->len] = '\0';
+}
+
+/*
+ * appendBinaryStringInfoNT
+ *
+ * Append arbitrary binary data to a StringInfo, allocating more space
+ * if necessary. Does not ensure a trailing null-byte exists.
+ */
+
+
+/*
+ * enlargeStringInfo
+ *
+ * Make sure there is enough space for 'needed' more bytes
+ * ('needed' does not include the terminating null).
+ *
+ * External callers usually need not concern themselves with this, since
+ * all stringinfo.c routines do it automatically.  However, if a caller
+ * knows that a StringInfo will eventually become X bytes large, it
+ * can save some palloc overhead by enlarging the buffer before starting
+ * to store data in it.
+ *
+ * NB: In the backend, because we use repalloc() to enlarge the buffer, the
+ * string buffer will remain allocated in the same memory context that was
+ * current when initStringInfo was called, even if another context is now
+ * current.  This is the desired and indeed critical behavior!
+ */
+void
+enlargeStringInfo(StringInfo str, int needed)
+{
+	int			newlen;
+
+	/*
+	 * Guard against out-of-range "needed" values.  Without this, we can get
+	 * an overflow or infinite loop in the following.
+	 */
+	if (needed < 0)				/* should not happen */
+	{
+#ifndef FRONTEND
+		elog(ERROR, "invalid string enlargement request size: %d", needed);
+#else
+		fprintf(stderr, "invalid string enlargement request size: %d\n", needed);
+		exit(EXIT_FAILURE);
+#endif
+	}
+	if (((Size) needed) >= (MaxAllocSize - (Size) str->len))
+	{
+#ifndef FRONTEND
+		ereport(ERROR,
+				(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
+				 errmsg("out of memory"),
+				 errdetail("Cannot enlarge string buffer containing %d bytes by %d more bytes.",
+						   str->len, needed)));
+#else
+		fprintf(stderr,
+				_("out of memory\n\nCannot enlarge string buffer containing %d bytes by %d more bytes.\n"),
+				str->len, needed);
+		exit(EXIT_FAILURE);
+#endif
+	}
+
+	needed += str->len + 1;		/* total space required now */
+
+	/* Because of the above test, we now have needed <= MaxAllocSize */
+
+	if (needed <= str->maxlen)
+		return;					/* got enough space already */
+
+	/*
+	 * We don't want to allocate just a little more space with each append;
+	 * for efficiency, double the buffer size each time it overflows.
+	 * Actually, we might need to more than double it if 'needed' is big...
+	 */
+	newlen = 2 * str->maxlen;
+	while (needed > newlen)
+		newlen = 2 * newlen;
+
+	/*
+	 * Clamp to MaxAllocSize in case we went past it.  Note we are assuming
+	 * here that MaxAllocSize <= INT_MAX/2, else the above loop could
+	 * overflow.  We will still have newlen >= needed.
+	 */
+	if (newlen > (int) MaxAllocSize)
+		newlen = (int) MaxAllocSize;
+
+	str->data = (char *) repalloc(str->data, newlen);
+
+	str->maxlen = newlen;
+}