From 98424c4460ea0bd1f0b530d0271f28315dcc84bb Mon Sep 17 00:00:00 2001 From: Greg Clayton Date: Mon, 6 Jul 2015 23:40:40 +0000 Subject: [PATCH] Make the "lldb/Utility/JSON.h" able to parse JSON into tokens with the new JSONParser class. Change over existing code to use this new parser so StructuredData can use the tokenizer to parse JSON instead of doing it manually. This allowed us to easily parse JSON into JSON* objects as well as into StructuredData. llvm-svn: 241522 --- lldb/include/lldb/Host/StringConvert.h | 2 + lldb/include/lldb/Utility/JSON.h | 68 +++- lldb/source/Core/StructuredData.cpp | 359 +++++------------ lldb/source/Host/common/StringConvert.cpp | 142 ++++--- lldb/source/Utility/JSON.cpp | 468 +++++++++++++++++++++- lldb/source/Utility/StringExtractor.cpp | 9 + lldb/source/Utility/StringExtractor.h | 12 + 7 files changed, 722 insertions(+), 338 deletions(-) diff --git a/lldb/include/lldb/Host/StringConvert.h b/lldb/include/lldb/Host/StringConvert.h index 3cc260cf2be1..af5c2a08db87 100644 --- a/lldb/include/lldb/Host/StringConvert.h +++ b/lldb/include/lldb/Host/StringConvert.h @@ -39,6 +39,8 @@ ToSInt64 (const char *s, int64_t fail_value = 0, int base = 0, bool *success_ptr uint64_t ToUInt64 (const char *s, uint64_t fail_value = 0, int base = 0, bool *success_ptr = nullptr); +double +ToDouble (const char *s, double fail_value = 0.0, bool *success_ptr = nullptr); } // namespace StringConvert } // namespace lldb_private diff --git a/lldb/include/lldb/Utility/JSON.h b/lldb/include/lldb/Utility/JSON.h index 45ddb71b5e03..b5b443b8033d 100644 --- a/lldb/include/lldb/Utility/JSON.h +++ b/lldb/include/lldb/Utility/JSON.h @@ -11,6 +11,7 @@ #define utility_JSON_h_ #include "lldb/Core/Stream.h" +#include "Utility/StringExtractor.h" #include #include @@ -22,6 +23,7 @@ #include "llvm/Support/Casting.h" namespace lldb_private { + class JSONValue { public: @@ -97,8 +99,9 @@ namespace lldb_private { { public: JSONNumber (); - JSONNumber (int64_t i); - + explicit JSONNumber (uint64_t i); + explicit JSONNumber (double d); + JSONNumber (const JSONNumber& s) = delete; JSONNumber& operator = (const JSONNumber& s) = delete; @@ -107,10 +110,19 @@ namespace lldb_private { Write (Stream& s); typedef std::shared_ptr SP; - - int64_t + + uint64_t GetData () { return m_data; } - + + double + GetAsDouble() + { + if (m_is_integer) + return (double)m_data; + else + return m_double; + } + static bool classof(const JSONValue *V) { return V->GetKind() == JSONValue::Kind::Number; @@ -120,7 +132,9 @@ namespace lldb_private { ~JSONNumber () = default; private: - int64_t m_data; + bool m_is_integer; + uint64_t m_data; + double m_double; }; class JSONTrue : public JSONValue @@ -271,6 +285,48 @@ namespace lldb_private { Vector m_elements; }; + + + class JSONParser : public StringExtractor + { + public: + enum Token + { + Invalid, + Error, + ObjectStart, + ObjectEnd, + ArrayStart, + ArrayEnd, + Comma, + Colon, + String, + Integer, + Float, + True, + False, + Null, + EndOfFile + }; + + JSONParser (const char *cstr); + + int + GetEscapedChar (bool &was_escaped); + + Token + GetToken (std::string &value); + + JSONValue::SP + ParseJSONValue (); + + protected: + JSONValue::SP + ParseJSONObject (); + + JSONValue::SP + ParseJSONArray (); + }; } #endif // utility_ProcessStructReader_h_ diff --git a/lldb/source/Core/StructuredData.cpp b/lldb/source/Core/StructuredData.cpp index a2c440948af1..efc104f1f3e8 100644 --- a/lldb/source/Core/StructuredData.cpp +++ b/lldb/source/Core/StructuredData.cpp @@ -14,301 +14,148 @@ #include #include "lldb/Core/StreamString.h" +#include "lldb/Host/StringConvert.h" +#include "lldb/Utility/JSON.h" using namespace lldb_private; -static StructuredData::ObjectSP read_json_object (const char **ch); -static StructuredData::ObjectSP read_json_array (const char **ch); +//---------------------------------------------------------------------- +// Functions that use a JSONParser to parse JSON into StructuredData +//---------------------------------------------------------------------- +static StructuredData::ObjectSP ParseJSONValue (JSONParser &json_parser); +static StructuredData::ObjectSP ParseJSONObject (JSONParser &json_parser); +static StructuredData::ObjectSP ParseJSONArray (JSONParser &json_parser); static StructuredData::ObjectSP -read_json_number (const char **ch) +ParseJSONObject (JSONParser &json_parser) { - StructuredData::ObjectSP object_sp; - while (isspace (**ch)) - (*ch)++; - const char *start_of_number = *ch; - bool is_integer = true; - bool is_float = false; - while (isdigit(**ch) || **ch == '-' || **ch == '.' || **ch == '+' || **ch == 'e' || **ch == 'E') - { - if (isdigit(**ch) == false && **ch != '-') - { - is_integer = false; - is_float = true; - } - (*ch)++; - } - while (isspace (**ch)) - (*ch)++; - if (**ch == ',' || **ch == ']' || **ch == '}') - { - if (is_integer) - { - errno = 0; - uint64_t val = strtoul (start_of_number, NULL, 10); - if (errno == 0) - { - object_sp.reset(new StructuredData::Integer()); - object_sp->GetAsInteger()->SetValue (val); - } - } - if (is_float) - { - char *end_of_number = NULL; - errno = 0; - double val = strtod (start_of_number, &end_of_number); - if (errno == 0 && end_of_number != start_of_number && end_of_number != NULL) - { - object_sp.reset(new StructuredData::Float()); - object_sp->GetAsFloat()->SetValue (val); - } - } - } - return object_sp; -} + // The "JSONParser::Token::ObjectStart" token should have already been consumed + // by the time this function is called + std::unique_ptr dict_up(new StructuredData::Dictionary()); -static std::string -read_json_string (const char **ch) -{ - std::string string; - if (**ch == '"') + std::string value; + std::string key; + while (1) { - (*ch)++; - while (**ch != '\0') - { - if (**ch == '"') - { - (*ch)++; - while (isspace (**ch)) - (*ch)++; - break; - } - else if (**ch == '\\') - { - switch (**ch) - { - case '"': - string.push_back('"'); - *ch += 2; - break; - case '\\': - string.push_back('\\'); - *ch += 2; - break; - case '/': - string.push_back('/'); - *ch += 2; - break; - case 'b': - string.push_back('\b'); - *ch += 2; - break; - case 'f': - string.push_back('\f'); - *ch += 2; - break; - case 'n': - string.push_back('\n'); - *ch += 2; - break; - case 'r': - string.push_back('\r'); - *ch += 2; - break; - case 't': - string.push_back('\t'); - *ch += 2; - break; - case 'u': - // FIXME handle four-hex-digits - *ch += 10; - break; - default: - *ch += 1; - } - } - else - { - string.push_back (**ch); - } - (*ch)++; - } - } - return string; -} + JSONParser::Token token = json_parser.GetToken(value); -static StructuredData::ObjectSP -read_json_value (const char **ch) -{ - StructuredData::ObjectSP object_sp; - while (isspace (**ch)) - (*ch)++; - - if (**ch == '{') - { - object_sp = read_json_object (ch); - } - else if (**ch == '[') - { - object_sp = read_json_array (ch); - } - else if (**ch == '"') - { - std::string string = read_json_string (ch); - object_sp.reset(new StructuredData::String()); - object_sp->GetAsString()->SetValue(string); - } - else - { - if (strncmp (*ch, "true", 4) == 0) + if (token == JSONParser::Token::String) { - object_sp.reset(new StructuredData::Boolean()); - object_sp->GetAsBoolean()->SetValue(true); - *ch += 4; + key.swap(value); + token = json_parser.GetToken(value); + if (token == JSONParser::Token::Colon) + { + StructuredData::ObjectSP value_sp = ParseJSONValue(json_parser); + if (value_sp) + dict_up->AddItem(key, value_sp); + else + break; + } } - else if (strncmp (*ch, "false", 5) == 0) + else if (token == JSONParser::Token::ObjectEnd) { - object_sp.reset(new StructuredData::Boolean()); - object_sp->GetAsBoolean()->SetValue(false); - *ch += 5; + return StructuredData::ObjectSP(dict_up.release()); } - else if (strncmp (*ch, "null", 4) == 0) + else if (token == JSONParser::Token::Comma) { - object_sp.reset(new StructuredData::Null()); - *ch += 4; + continue; } else { - object_sp = read_json_number (ch); + break; } } - return object_sp; + return StructuredData::ObjectSP(); } static StructuredData::ObjectSP -read_json_array (const char **ch) +ParseJSONArray (JSONParser &json_parser) { - StructuredData::ObjectSP object_sp; - if (**ch == '[') - { - (*ch)++; - while (isspace (**ch)) - (*ch)++; + // The "JSONParser::Token::ObjectStart" token should have already been consumed + // by the time this function is called + std::unique_ptr array_up(new StructuredData::Array()); - bool first_value = true; - while (**ch != '\0' && (first_value || **ch == ',')) + std::string value; + std::string key; + while (1) + { + StructuredData::ObjectSP value_sp = ParseJSONValue(json_parser); + if (value_sp) + array_up->AddItem(value_sp); + else + break; + + JSONParser::Token token = json_parser.GetToken(value); + if (token == JSONParser::Token::Comma) { - if (**ch == ',') - (*ch)++; - first_value = false; - while (isspace (**ch)) - (*ch)++; - lldb_private::StructuredData::ObjectSP value_sp = read_json_value (ch); - if (value_sp) - { - if (object_sp.get() == NULL) - { - object_sp.reset(new StructuredData::Array()); - } - object_sp->GetAsArray()->Push (value_sp); - } - while (isspace (**ch)) - (*ch)++; + continue; } - if (**ch == ']') + else if (token == JSONParser::Token::ArrayEnd) { - // FIXME should throw an error if we don't see a } to close out the JSON object - (*ch)++; - while (isspace (**ch)) - (*ch)++; + return StructuredData::ObjectSP(array_up.release()); + } + else + { + break; } } - return object_sp; + return StructuredData::ObjectSP(); } static StructuredData::ObjectSP -read_json_object (const char **ch) +ParseJSONValue (JSONParser &json_parser) { - StructuredData::ObjectSP object_sp; - if (**ch == '{') + std::string value; + const JSONParser::Token token = json_parser.GetToken(value); + switch (token) { - (*ch)++; - while (isspace (**ch)) - (*ch)++; - bool first_pair = true; - while (**ch != '\0' && (first_pair || **ch == ',')) - { - first_pair = false; - if (**ch == ',') - (*ch)++; - while (isspace (**ch)) - (*ch)++; - if (**ch != '"') - break; - std::string key_string = read_json_string (ch); - while (isspace (**ch)) - (*ch)++; - if (key_string.size() > 0 && **ch == ':') - { - (*ch)++; - while (isspace (**ch)) - (*ch)++; - lldb_private::StructuredData::ObjectSP value_sp = read_json_value (ch); - if (value_sp.get()) - { - if (object_sp.get() == NULL) - { - object_sp.reset(new StructuredData::Dictionary()); - } - object_sp->GetAsDictionary()->AddItem (key_string.c_str(), value_sp); - } - } - while (isspace (**ch)) - (*ch)++; - } - if (**ch == '}') - { - // FIXME should throw an error if we don't see a } to close out the JSON object - (*ch)++; - while (isspace (**ch)) - (*ch)++; - } - } - return object_sp; -} + case JSONParser::Token::ObjectStart: + return ParseJSONObject(json_parser); + case JSONParser::Token::ArrayStart: + return ParseJSONArray(json_parser); + + case JSONParser::Token::Integer: + { + bool success = false; + uint64_t uval = StringConvert::ToUInt64(value.c_str(), 0, 0, &success); + if (success) + return StructuredData::ObjectSP(new StructuredData::Integer(uval)); + } + break; + + case JSONParser::Token::Float: + { + bool success = false; + double val = StringConvert::ToDouble(value.c_str(), 0.0, &success); + if (success) + return StructuredData::ObjectSP(new StructuredData::Float(val)); + } + break; + + case JSONParser::Token::String: + return StructuredData::ObjectSP(new StructuredData::String(value)); + + case JSONParser::Token::True: + case JSONParser::Token::False: + return StructuredData::ObjectSP(new StructuredData::Boolean(token == JSONParser::Token::True)); + + case JSONParser::Token::Null: + return StructuredData::ObjectSP(new StructuredData::Null()); + + default: + break; + } + return StructuredData::ObjectSP(); + +} StructuredData::ObjectSP StructuredData::ParseJSON (std::string json_text) { - StructuredData::ObjectSP object_sp; - const size_t json_text_size = json_text.size(); - if (json_text_size > 0) - { - const char *start_of_json_text = json_text.c_str(); - const char *c = json_text.c_str(); - while (*c != '\0' && - static_cast(c - start_of_json_text) <= json_text_size) - { - while (isspace (*c) && - static_cast(c - start_of_json_text) < json_text_size) - c++; - if (*c == '{') - { - object_sp = read_json_object (&c); - } - else if (*c == '[') - { - object_sp = read_json_array (&c); - } - else - { - // We have bad characters here, this is likely an illegal JSON string. - return object_sp; - } - } - } + JSONParser json_parser(json_text.c_str()); + StructuredData::ObjectSP object_sp = ParseJSONValue(json_parser); return object_sp; } @@ -395,7 +242,7 @@ StructuredData::Integer::Dump (Stream &s) const void StructuredData::Float::Dump (Stream &s) const { - s.Printf ("%lf", m_value); + s.Printf ("%lg", m_value); } void diff --git a/lldb/source/Host/common/StringConvert.cpp b/lldb/source/Host/common/StringConvert.cpp index 0a8e75f4b877..c4ff67515d4e 100644 --- a/lldb/source/Host/common/StringConvert.cpp +++ b/lldb/source/Host/common/StringConvert.cpp @@ -15,79 +15,103 @@ // Project includes #include "lldb/Host/StringConvert.h" -namespace lldb_private { - -namespace StringConvert { - -int32_t -ToSInt32 (const char *s, int32_t fail_value, int base, bool *success_ptr) +namespace lldb_private { - if (s && s[0]) + namespace StringConvert { - char *end = nullptr; - const long sval = ::strtol (s, &end, base); - if (*end == '\0') + + int32_t + ToSInt32 (const char *s, int32_t fail_value, int base, bool *success_ptr) { + if (s && s[0]) + { + char *end = nullptr; + const long sval = ::strtol (s, &end, base); + if (*end == '\0') + { + if (success_ptr) + *success_ptr = ((sval <= INT32_MAX) && (sval >= INT32_MIN)); + return (int32_t)sval; // All characters were used, return the result + } + } if (success_ptr) - *success_ptr = ((sval <= INT32_MAX) && (sval >= INT32_MIN)); - return (int32_t)sval; // All characters were used, return the result + *success_ptr = false; + return fail_value; } - } - if (success_ptr) *success_ptr = false; - return fail_value; -} -uint32_t -ToUInt32 (const char *s, uint32_t fail_value, int base, bool *success_ptr) -{ - if (s && s[0]) - { - char *end = nullptr; - const unsigned long uval = ::strtoul (s, &end, base); - if (*end == '\0') + uint32_t + ToUInt32 (const char *s, uint32_t fail_value, int base, bool *success_ptr) { + if (s && s[0]) + { + char *end = nullptr; + const unsigned long uval = ::strtoul (s, &end, base); + if (*end == '\0') + { + if (success_ptr) + *success_ptr = (uval <= UINT32_MAX); + return (uint32_t)uval; // All characters were used, return the result + } + } if (success_ptr) - *success_ptr = (uval <= UINT32_MAX); - return (uint32_t)uval; // All characters were used, return the result + *success_ptr = false; + return fail_value; } - } - if (success_ptr) *success_ptr = false; - return fail_value; -} -int64_t -ToSInt64 (const char *s, int64_t fail_value, int base, bool *success_ptr) -{ - if (s && s[0]) - { - char *end = nullptr; - int64_t uval = ::strtoll (s, &end, base); - if (*end == '\0') + int64_t + ToSInt64 (const char *s, int64_t fail_value, int base, bool *success_ptr) { - if (success_ptr) *success_ptr = true; - return uval; // All characters were used, return the result + if (s && s[0]) + { + char *end = nullptr; + int64_t uval = ::strtoll (s, &end, base); + if (*end == '\0') + { + if (success_ptr) + *success_ptr = true; + return uval; // All characters were used, return the result + } + } + if (success_ptr) + *success_ptr = false; + return fail_value; } - } - if (success_ptr) *success_ptr = false; - return fail_value; -} -uint64_t -ToUInt64 (const char *s, uint64_t fail_value, int base, bool *success_ptr) -{ - if (s && s[0]) - { - char *end = nullptr; - uint64_t uval = ::strtoull (s, &end, base); - if (*end == '\0') + uint64_t + ToUInt64 (const char *s, uint64_t fail_value, int base, bool *success_ptr) { - if (success_ptr) *success_ptr = true; - return uval; // All characters were used, return the result + if (s && s[0]) + { + char *end = nullptr; + uint64_t uval = ::strtoull (s, &end, base); + if (*end == '\0') + { + if (success_ptr) + *success_ptr = true; + return uval; // All characters were used, return the result + } + } + if (success_ptr) *success_ptr = false; + return fail_value; + } + + double + ToDouble (const char *s, double fail_value, bool *success_ptr) + { + if (s && s[0]) + { + char *end = nullptr; + double val = strtod (s, &end); + if (*end == '\0') + { + if (success_ptr) + *success_ptr = true; + return val; // All characters were used, return the result + } + } + if (success_ptr) + *success_ptr = false; + return fail_value; } } - if (success_ptr) *success_ptr = false; - return fail_value; -} - -} } diff --git a/lldb/source/Utility/JSON.cpp b/lldb/source/Utility/JSON.cpp index 0ba8cf4399ce..eaf224d555f0 100644 --- a/lldb/source/Utility/JSON.cpp +++ b/lldb/source/Utility/JSON.cpp @@ -8,6 +8,8 @@ //===----------------------------------------------------------------------===// #include "lldb/Utility/JSON.h" +#include "lldb/Core/StreamString.h" +#include "lldb/Host/StringConvert.h" using namespace lldb_private; @@ -33,20 +35,20 @@ JSONString::json_string_quote_metachars (const std::string &s) } JSONString::JSONString () : -JSONValue(JSONValue::Kind::String), -m_data() + JSONValue(JSONValue::Kind::String), + m_data() { } JSONString::JSONString (const char* s) : -JSONValue(JSONValue::Kind::String), -m_data(s ? s : "") + JSONValue(JSONValue::Kind::String), + m_data(s ? s : "") { } JSONString::JSONString (const std::string& s) : -JSONValue(JSONValue::Kind::String), -m_data(s) + JSONValue(JSONValue::Kind::String), + m_data(s) { } @@ -57,25 +59,41 @@ JSONString::Write (Stream& s) } JSONNumber::JSONNumber () : -JSONValue(JSONValue::Kind::Number), -m_data(0) + JSONValue(JSONValue::Kind::Number), + m_is_integer(true), + m_data(0), + m_double(0.0) { } -JSONNumber::JSONNumber (int64_t i) : -JSONValue(JSONValue::Kind::Number), -m_data(i) +JSONNumber::JSONNumber (uint64_t i) : + JSONValue(JSONValue::Kind::Number), + m_is_integer(true), + m_data(i), + m_double(0.0) +{ +} + + +JSONNumber::JSONNumber (double d) : + JSONValue(JSONValue::Kind::Number), + m_is_integer(false), + m_data(0), + m_double(d) { } void JSONNumber::Write (Stream& s) { - s.Printf("%" PRId64, m_data); + if (m_is_integer) + s.Printf("%" PRIu64, m_data); + else + s.Printf("%g", m_double); } JSONTrue::JSONTrue () : -JSONValue(JSONValue::Kind::True) + JSONValue(JSONValue::Kind::True) { } @@ -86,7 +104,7 @@ JSONTrue::Write(Stream& s) } JSONFalse::JSONFalse () : -JSONValue(JSONValue::Kind::False) + JSONValue(JSONValue::Kind::False) { } @@ -97,7 +115,7 @@ JSONFalse::Write(Stream& s) } JSONNull::JSONNull () : -JSONValue(JSONValue::Kind::Null) + JSONValue(JSONValue::Kind::Null) { } @@ -108,7 +126,7 @@ JSONNull::Write(Stream& s) } JSONObject::JSONObject () : -JSONValue(JSONValue::Kind::Object) + JSONValue(JSONValue::Kind::Object) { } @@ -153,7 +171,7 @@ JSONObject::GetObject (const std::string& key) } JSONArray::JSONArray () : -JSONValue(JSONValue::Kind::Array) + JSONValue(JSONValue::Kind::Array) { } @@ -215,3 +233,419 @@ JSONArray::GetNumElements () { return m_elements.size(); } + + +JSONParser::JSONParser (const char *cstr) : + StringExtractor(cstr) +{ +} + +JSONParser::Token +JSONParser::GetToken (std::string &value) +{ + StreamString error; + + value.clear(); + SkipSpaces (); + const uint64_t start_index = m_index; + const char ch = GetChar(); + switch (ch) + { + case '{': return Token::ObjectStart; + case '}': return Token::ObjectEnd; + case '[': return Token::ArrayStart; + case ']': return Token::ArrayEnd; + case ',': return Token::Comma; + case ':': return Token::Colon; + case '\0': return Token::EndOfFile; + case 't': + if (GetChar() == 'r') + if (GetChar() == 'u') + if (GetChar() == 'e') + return Token::True; + break; + + case 'f': + if (GetChar() == 'a') + if (GetChar() == 'l') + if (GetChar() == 's') + if (GetChar() == 'e') + return Token::False; + break; + + case 'n': + if (GetChar() == 'u') + if (GetChar() == 'l') + if (GetChar() == 'l') + return Token::Null; + break; + + case '"': + { + while (1) + { + bool was_escaped = false; + int escaped_ch = GetEscapedChar(was_escaped); + if (escaped_ch == -1) + { + error.Printf("error: an error occurred getting a character from offset %" PRIu64, start_index); + value = std::move(error.GetString()); + return Token::Error; + + } + else + { + const bool is_end_quote = escaped_ch == '"'; + const bool is_null = escaped_ch == 0; + if (was_escaped || (!is_end_quote && !is_null)) + { + if (CHAR_MIN <= escaped_ch && escaped_ch <= CHAR_MAX) + { + value.append(1, (char)escaped_ch); + } + else + { + error.Printf("error: wide character support is needed for unicode character 0x%4.4x at offset %" PRIu64, escaped_ch, start_index); + value = std::move(error.GetString()); + return Token::Error; + } + } + else if (is_end_quote) + { + return Token::String; + } + else if (is_null) + { + value = "error: missing end quote for string"; + return Token::Error; + } + } + } + } + break; + + case '-': + case '0': + case '1': + case '2': + case '3': + case '4': + case '5': + case '6': + case '7': + case '8': + case '9': + { + bool done = false; + bool got_decimal_point = false; + uint64_t exp_index = 0; + bool got_int_digits = (ch >= '0') && (ch <= '9'); + bool got_frac_digits = false; + bool got_exp_digits = false; + while (!done) + { + const char next_ch = PeekChar(); + switch (next_ch) + { + case '0': + case '1': + case '2': + case '3': + case '4': + case '5': + case '6': + case '7': + case '8': + case '9': + if (exp_index != 0) + { + got_exp_digits = true; + } + else if (got_decimal_point) + { + got_frac_digits = true; + } + else + { + got_int_digits = true; + } + ++m_index; // Skip this character + break; + + case '.': + if (got_decimal_point) + { + error.Printf("error: extra decimal point found at offset %" PRIu64, start_index); + value = std::move(error.GetString()); + return Token::Error; + } + else + { + got_decimal_point = true; + ++m_index; // Skip this character + } + break; + + case 'e': + case 'E': + if (exp_index != 0) + { + error.Printf("error: extra expenent character found at offset %" PRIu64, start_index); + value = std::move(error.GetString()); + return Token::Error; + } + else + { + exp_index = m_index; + ++m_index; // Skip this character + } + break; + + case '+': + case '-': + // The '+' and '-' can only come after an exponent character... + if (exp_index == m_index - 1) + { + ++m_index; // Skip the exponent sign character + } + else + { + error.Printf("error: unexpected %c character at offset %" PRIu64, next_ch, start_index); + value = std::move(error.GetString()); + return Token::Error; + } + + default: + done = true; + break; + } + } + + if (m_index > start_index) + { + value = m_packet.substr(start_index, m_index - start_index); + if (got_decimal_point) + { + if (exp_index != 0) + { + // We have an exponent, make sure we got exponent digits + if (got_exp_digits) + { + return Token::Float; + } + else + { + error.Printf("error: got exponent character but no exponent digits at offset in float value \"%s\"", value.c_str()); + value = std::move(error.GetString()); + return Token::Error; + } + } + else + { + // No exponent, but we need at least one decimal after the decimal point + if (got_frac_digits) + { + return Token::Float; + } + else + { + error.Printf("error: no digits after decimal point \"%s\"", value.c_str()); + value = std::move(error.GetString()); + return Token::Error; + } + } + } + else + { + // No decimal point + if (got_int_digits) + { + // We need at least some integer digits to make an integer + return Token::Integer; + } + else + { + error.Printf("error: no digits negate sign \"%s\"", value.c_str()); + value = std::move(error.GetString()); + return Token::Error; + } + } + } + else + { + error.Printf("error: invalid number found at offset %" PRIu64, start_index); + value = std::move(error.GetString()); + return Token::Error; + } + } + break; + default: + break; + } + error.Printf("error: failed to parse token at offset %" PRIu64 " (around character '%c')", start_index, ch); + value = std::move(error.GetString()); + return Token::Error; +} + +int +JSONParser::GetEscapedChar(bool &was_escaped) +{ + was_escaped = false; + const char ch = GetChar(); + if (ch == '\\') + { + was_escaped = true; + const char ch2 = GetChar(); + switch (ch2) + { + case '"': + case '\\': + case '/': + default: + break; + + case 'b': return '\b'; + case 'f': return '\f'; + case 'n': return '\n'; + case 'r': return '\r'; + case 't': return '\t'; + case 'u': + { + const int hi_byte = DecodeHexU8(); + const int lo_byte = DecodeHexU8(); + if (hi_byte >=0 && lo_byte >= 0) + return hi_byte << 8 | lo_byte; + return -1; + } + break; + } + return ch2; + } + return ch; +} + +JSONValue::SP +JSONParser::ParseJSONObject () +{ + // The "JSONParser::Token::ObjectStart" token should have already been consumed + // by the time this function is called + std::unique_ptr dict_up(new JSONObject()); + + std::string value; + std::string key; + while (1) + { + JSONParser::Token token = GetToken(value); + + if (token == JSONParser::Token::String) + { + key.swap(value); + token = GetToken(value); + if (token == JSONParser::Token::Colon) + { + JSONValue::SP value_sp = ParseJSONValue(); + if (value_sp) + dict_up->SetObject(key, value_sp); + else + break; + } + } + else if (token == JSONParser::Token::ObjectEnd) + { + return JSONValue::SP(dict_up.release()); + } + else if (token == JSONParser::Token::Comma) + { + continue; + } + else + { + break; + } + } + return JSONValue::SP(); +} + +JSONValue::SP +JSONParser::ParseJSONArray () +{ + // The "JSONParser::Token::ObjectStart" token should have already been consumed + // by the time this function is called + std::unique_ptr array_up(new JSONArray()); + + std::string value; + std::string key; + while (1) + { + JSONValue::SP value_sp = ParseJSONValue(); + if (value_sp) + array_up->AppendObject(value_sp); + else + break; + + JSONParser::Token token = GetToken(value); + if (token == JSONParser::Token::Comma) + { + continue; + } + else if (token == JSONParser::Token::ArrayEnd) + { + return JSONValue::SP(array_up.release()); + } + else + { + break; + } + } + return JSONValue::SP(); +} + +JSONValue::SP +JSONParser::ParseJSONValue () +{ + std::string value; + const JSONParser::Token token = GetToken(value); + switch (token) + { + case JSONParser::Token::ObjectStart: + return ParseJSONObject(); + + case JSONParser::Token::ArrayStart: + return ParseJSONArray(); + + case JSONParser::Token::Integer: + { + bool success = false; + uint64_t uval = StringConvert::ToUInt64(value.c_str(), 0, 0, &success); + if (success) + return JSONValue::SP(new JSONNumber(uval)); + } + break; + + case JSONParser::Token::Float: + { + bool success = false; + double val = StringConvert::ToDouble(value.c_str(), 0.0, &success); + if (success) + return JSONValue::SP(new JSONNumber(val)); + } + break; + + case JSONParser::Token::String: + return JSONValue::SP(new JSONString(value)); + + case JSONParser::Token::True: + return JSONValue::SP(new JSONTrue()); + + case JSONParser::Token::False: + return JSONValue::SP(new JSONFalse()); + + case JSONParser::Token::Null: + return JSONValue::SP(new JSONNull()); + + default: + break; + } + return JSONValue::SP(); + +} diff --git a/lldb/source/Utility/StringExtractor.cpp b/lldb/source/Utility/StringExtractor.cpp index e82c83dfd093..bde5e1961d8a 100644 --- a/lldb/source/Utility/StringExtractor.cpp +++ b/lldb/source/Utility/StringExtractor.cpp @@ -476,3 +476,12 @@ StringExtractor::GetNameColonValue (std::string &name, std::string &value) m_index = UINT64_MAX; return false; } + +void +StringExtractor::SkipSpaces () +{ + const size_t n = m_packet.size(); + while (m_index < n && isspace(m_packet[m_index])) + ++m_index; +} + diff --git a/lldb/source/Utility/StringExtractor.h b/lldb/source/Utility/StringExtractor.h index 49dfe99bd358..0f2dbb166be1 100644 --- a/lldb/source/Utility/StringExtractor.h +++ b/lldb/source/Utility/StringExtractor.h @@ -67,6 +67,9 @@ public: m_index = 0; } + void + SkipSpaces (); + std::string & GetStringRef () { @@ -96,6 +99,15 @@ public: char GetChar (char fail_value = '\0'); + char + PeekChar (char fail_value = '\0') + { + const char *cstr = Peek(); + if (cstr) + return cstr[0]; + return fail_value; + } + int DecodeHexU8();