pgLab/SqlSyntaxHighlighter.cpp

263 lines
8.5 KiB
C++

#include "SqlSyntaxHighlighter.h"
#include "pgtypecontainer.h"
namespace {
enum class BasicTokenType {
None,
End, // End of input
Symbol, // can be many things, keyword, object name, operator, ..
Comment,
QuotedString,
DollarQuotedString,
QuotedIdentifier
};
enum class LexerState {
Null,
InDollarQuotedString
};
class Lexer {
private:
QString m_block;
int m_pos = -1;
LexerState m_state;
public:
Lexer(const QString &block, LexerState currentstate)
: m_block(block)
, m_state(currentstate)
{}
QChar nextChar()
{
QChar result = QChar::Null;
if (m_pos+1 < m_block.size()) {
result = m_block.at(++m_pos);
}
else {
++m_pos;
}
return result;
}
QChar peekChar()
{
QChar result = QChar::Null;
if (m_pos+1 < m_block.size()) {
result = m_block.at(m_pos+1);
}
return result;
}
/**
* @brief NextBasicToken
* @param in
* @param ofs
* @param start
* @param length
* @return false when input seems invalid, it will return what it did recognize but something wasn't right, parser should try to recover
*/
bool nextBasicToken(int &startpos, int &length, BasicTokenType &tokentype, QString &out)
{
// Basically chops based on white space
// it does also recognize comments and quoted strings/identifiers
bool result = false;
while (true) {
QChar c = nextChar();
if (c.isSpace()) {
// Just skip whitespace
}
else if (c == '-' && peekChar() == '-') { // two dashes, start of comment
startpos = m_pos;
// Loop till end of line or end of block
c = nextChar();
while (c != QChar::Null && c != '\n') {
c = nextChar();
}
length = m_pos - startpos;
tokentype = BasicTokenType::Comment;
return true;
}
else if (c == '\'') {
startpos = m_pos;
// Single quoted string so it's an SQL text literal
while (true) {
c = nextChar();
if (c == QChar::Null || c == '\n') {
// unexpected end, pretend nothings wrong
length = m_pos - startpos;
tokentype = BasicTokenType::QuotedString;
return true;
}
else if (c == '\'') {
// maybe end of string literal
if (peekChar() == '\'') {
// Nope, just double quote to escape quote
nextChar(); // eat it
}
else {
length = m_pos - startpos;
tokentype = BasicTokenType::QuotedString;
return true;
}
}
}
}
else if (c == '"') {
startpos = m_pos;
// Double quoted identifier
while (true) {
c = nextChar();
if (c == QChar::Null || c == '\n') {
// unexpected end, pretend nothings wrong
length = m_pos - startpos;
tokentype = BasicTokenType::QuotedIdentifier;
return true;
}
else if (c == '"') {
// maybe end of string literal
if (peekChar() == '"') {
// Nope, just double quote to escape quote
nextChar(); // eat it
}
else {
length = m_pos - startpos;
tokentype = BasicTokenType::QuotedIdentifier;
return true;
}
}
}
}
else if (c == QChar::Null) {
break;
}
else {
startpos = m_pos;
// Undetermined symbol
while (!c.isSpace() && c != QChar::Null) {
c = nextChar();
}
length = m_pos - startpos;
tokentype = BasicTokenType::Symbol;
QStringRef sr(&m_block, startpos, length);
out = sr.toString();
return true;
}
}
return false;
}
};
t_SymbolSet g_Keywords = {
"a", "abort", "abs", "absent", "absolute", "access", "according", "action", "ada", "add",
"admin", "after", "aggregate", "all", "allocate", "also", "alter", "analyse", "analyze", "and",
"any", "are", "array", "array_agg", "array_max_cardinality", "as", "asc", "asensitive",
"assetion", "assignment", "asymmetric", "at", "atomic", "attribute", "attributes", "authorization", "avg",
"backward", "base64", "before", "begin", "begin_frame", "begin_partition", "bernoulli", "between", "binary",
"bit", "bit_length", "blob", "blocked", "bom", "boolean", "both", "breadth", "buffer", "by",
"c", "cache", "call", "called", "cardinality", "cascade", "cascaded", "case", "cast",
"catalog", "catalog_name", "ceil", "ceiling", "chain", "char", "character", "characteristics",
"characters", "character_length", "character_set_catalog", "character_set_name", "character_set_schema",
"char_length", "check", "checkpoint", "class", "class_origin", "clob", "close", "cluster",
"coalesce", "cobol", "collate", "collation", "collation_catalog", "collation_name", "collation_schema",
"collect", "column", "columns", "column_name", "command_function", "command_function_code",
"comment", "comments", "commit", "committed", "concurrently", "condition", "condition_number",
"configuration", "conflict", "connect", "connection", "connection_name", "constraint", "constraints",
"constraint_catalog", "constraint_name", "constraint_schema", "constructor", "contains", "content",
"continue", "control", "conversion", "convert", "copy", "corr", "corresponding", "cost", "count",
"covar_pop", "covar_samp", "create", "cross", "csv", "cube", "cume_dist", "current", "current_catalog",
"current_date", "current_default_transform_group", "current_path", "current_role", "current_row",
"current_schema", "current_time", "current_timestamp", "current_transform_group_for_type",
"current_user", "cursor", "cursor_name", "cycle",
"data", "database", "datalink", "date", "datetime_interval_code", "datetime_interval_precision",
"day", "db", "deallocate", "dec", "decimal", "declare", "default", "defaults", "deferrable", "deferred",
"defined", "definer", "degree", "delete", "delimiter", "delimiters", "dense_rank", "depends", "depth",
"deref", "derived", "desc", "describe", "descriptor", "deterministic", "diagnostics", "dictionary",
"disable", "discard", "disconnect", "dispatch", "distinct", "dlnewcopy", "dlpreviouscopy", "dlurlcomplete",
"dlurlcompleteonly", "dlurlcompletewrite", "dlurlpatch", "dlurlpathonly", "dlurlpathwrite", "dlurlscheme",
"dlurlserver", "do", "domain", "drop",
"elif", "end", "event", "exclude", "execute", "exists", "extenstion",
"fetch", "first", "foreign", "from", "function", "full",
"global", "grant", "group",
"having",
"if", "ilike", "immediate", "in", "index", "inherits", "initially", "inner", "insert", "into", "is",
"join",
"key",
"language", "last", "left", "like", "limit", "listen", "local", "lock",
"match",
"natural", "not", "null", "nulls",
"offset", "oids", "on", "or", "order", "outer", "over",
"partial", "partition", "prepare", "preserve", "primary", "privileges", "public",
"references", "refresh", "reindex", "release", "replace", "reset", "restrict", "revoke", "right", "role", "rollback", "row", "rows", "rule",
"savepoint", "schema", "select", "sequence", "server", "set", "show", "simple", "statement",
"table", "tablespace", "temp", "temporary", "trigger", "truncate",
"unique", "unlisten", "unlogged", "update", "user", "using",
"vacuum", "values", "view", "volatile",
"when", "where", "with", "wrapper"
};
//"bigint",
}
SqlSyntaxHighlighter::SqlSyntaxHighlighter(QTextDocument *parent)
: QSyntaxHighlighter(parent)
{
m_keywordFormat.setForeground(QColor(32, 32, 192));
m_keywordFormat.setFontWeight(QFont::Bold);
m_commentFormat.setForeground(QColor(64, 64, 64));
m_quotedStringFormat.setForeground(QColor(192, 32, 192));
m_typeFormat.setForeground(QColor(32, 192, 32));
m_typeFormat.setFontWeight(QFont::Bold);
}
SqlSyntaxHighlighter::~SqlSyntaxHighlighter()
{
}
void SqlSyntaxHighlighter::setTypes(const PgTypeContainer *types)
{
m_typeNames.clear();
for (auto &e : *types) {
m_typeNames.insert(e.typname);
}
}
void SqlSyntaxHighlighter::highlightBlock(const QString &text)
{
Lexer lexer(text, LexerState::Null);
int startpos, length;
BasicTokenType tokentype;
QString s;
while (lexer.nextBasicToken(startpos, length, tokentype, s)) {
switch (tokentype) {
case BasicTokenType::None:
case BasicTokenType::End: // End of input
case BasicTokenType::DollarQuotedString:
break;
case BasicTokenType::Symbol: // can be many things, keyword, object name, operator, ..
if (g_Keywords.count(s.toLower()) > 0) {
setFormat(startpos, length, m_keywordFormat);
}
else if (m_typeNames.count(s.toLower()) > 0) {
setFormat(startpos, length, m_typeFormat);
}
break;
case BasicTokenType::Comment:
setFormat(startpos, length, m_commentFormat);
break;
case BasicTokenType::QuotedString:
setFormat(startpos, length, m_quotedStringFormat);
break;
case BasicTokenType::QuotedIdentifier:
break;
}
}
}