/* * Copyright (C) Igor Sysoev */ #include #include #include static uint32_t usual[] = { 0xffffdbfe, /* 1111 1111 1111 1111 1101 1011 1111 1110 */ /* ?>=< ;:98 7654 3210 /.-, +*)( '&%$ #"! */ 0x7fff37d6, /* 0111 1111 1111 1111 0011 0111 1101 0110 */ /* _^]\ [ZYX WVUT SRQP ONML KJIH GFED CBA@ */ #if (NGX_WIN32) 0xefffffff, /* 1110 1111 1111 1111 1111 1111 1111 1111 */ #else 0xffffffff, /* 1111 1111 1111 1111 1111 1111 1111 1111 */ #endif /* ~}| {zyx wvut srqp onml kjih gfed cba` */ 0xffffffff, /* 1111 1111 1111 1111 1111 1111 1111 1111 */ 0xffffffff, /* 1111 1111 1111 1111 1111 1111 1111 1111 */ 0xffffffff, /* 1111 1111 1111 1111 1111 1111 1111 1111 */ 0xffffffff, /* 1111 1111 1111 1111 1111 1111 1111 1111 */ 0xffffffff /* 1111 1111 1111 1111 1111 1111 1111 1111 */ }; /* gcc, icc, msvc and others compile these switches as an jump table */ ngx_int_t ngx_http_parse_request_line(ngx_http_request_t *r, ngx_buf_t *b) { u_char c, ch, *p, *m; enum { sw_start = 0, sw_method, sw_spaces_before_uri, sw_schema, sw_schema_slash, sw_schema_slash_slash, sw_host, sw_port, sw_after_slash_in_uri, sw_check_uri, sw_uri, sw_http_09, sw_http_H, sw_http_HT, sw_http_HTT, sw_http_HTTP, sw_first_major_digit, sw_major_digit, sw_first_minor_digit, sw_minor_digit, sw_almost_done } state; state = r->state; for (p = b->pos; p < b->last; p++) { ch = *p; switch (state) { /* HTTP methods: GET, HEAD, POST */ case sw_start: r->request_start = p; if (ch == CR || ch == LF) { break; } if (ch < 'A' || ch > 'Z') { return NGX_HTTP_PARSE_INVALID_METHOD; } state = sw_method; break; case sw_method: if (ch == ' ') { r->method_end = p - 1; m = r->request_start; switch (p - m) { case 3: if (m[0] == 'G' && m[1] == 'E' && m[2] == 'T') { r->method = NGX_HTTP_GET; break; } if (m[0] == 'P' && m[1] == 'U' && m[2] == 'T') { r->method = NGX_HTTP_PUT; break; } break; case 4: if (m[1] == 'O') { if (m[0] == 'P' && m[2] == 'S' && m[3] == 'T') { r->method = NGX_HTTP_POST; break; } if (m[0] == 'C' && m[2] == 'P' && m[3] == 'Y') { r->method = NGX_HTTP_COPY; break; } if (m[0] == 'M' && m[2] == 'V' && m[3] == 'E') { r->method = NGX_HTTP_MOVE; break; } if (m[0] == 'L' && m[2] == 'C' && m[3] == 'K') { r->method = NGX_HTTP_LOCK; break; } } else { if (m[0] == 'H' && m[1] == 'E' && m[2] == 'A' && m[3] == 'D') { r->method = NGX_HTTP_HEAD; break; } } break; case 5: if (m[0] == 'M' && m[1] == 'K' && m[2] == 'C' && m[3] == 'O' && m[4] == 'L') { r->method = NGX_HTTP_MKCOL; } if (m[0] == 'T' && m[1] == 'R' && m[2] == 'A' && m[3] == 'C' && m[4] == 'E') { r->method = NGX_HTTP_TRACE; } break; case 6: if (m[0] == 'D' && m[1] == 'E' && m[2] == 'L' && m[3] == 'E' && m[4] == 'T' && m[5] == 'E') { r->method = NGX_HTTP_DELETE; break; } if (m[0] == 'U' && m[1] == 'N' && m[2] == 'L' && m[3] == 'O' && m[4] == 'C' && m[5] == 'K') { r->method = NGX_HTTP_UNLOCK; break; } break; case 7: if (m[0] == 'O' && m[1] == 'P' && m[2] == 'T' && m[3] == 'I' && m[4] == 'O' && m[5] == 'N' && m[6] == 'S') { r->method = NGX_HTTP_OPTIONS; } break; case 8: if (m[0] == 'P' && m[1] == 'R' && m[2] == 'O' && m[3] == 'P' && m[4] == 'F' && m[5] == 'I' && m[6] == 'N' && m[7] == 'D') { r->method = NGX_HTTP_PROPFIND; } break; case 9: if (m[0] == 'P' && m[1] == 'R' && m[2] == 'O' && m[3] == 'P' && m[4] == 'P' && m[5] == 'A' && m[6] == 'T' && m[7] == 'C' && m[8] == 'H') { r->method = NGX_HTTP_PROPPATCH; } break; } state = sw_spaces_before_uri; break; } if (ch < 'A' || ch > 'Z') { return NGX_HTTP_PARSE_INVALID_METHOD; } break; /* space* before URI */ case sw_spaces_before_uri: if (ch == '/' ){ r->uri_start = p; state = sw_after_slash_in_uri; break; } c = (u_char) (ch | 0x20); if (c >= 'a' && c <= 'z') { r->schema_start = p; state = sw_schema; break; } switch (ch) { case ' ': break; default: return NGX_HTTP_PARSE_INVALID_REQUEST; } break; case sw_schema: c = (u_char) (ch | 0x20); if (c >= 'a' && c <= 'z') { break; } switch (ch) { case ':': r->schema_end = p; state = sw_schema_slash; break; default: return NGX_HTTP_PARSE_INVALID_REQUEST; } break; case sw_schema_slash: switch (ch) { case '/': state = sw_schema_slash_slash; break; default: return NGX_HTTP_PARSE_INVALID_REQUEST; } break; case sw_schema_slash_slash: switch (ch) { case '/': r->host_start = p + 1; state = sw_host; break; default: return NGX_HTTP_PARSE_INVALID_REQUEST; } break; case sw_host: c = (u_char) (ch | 0x20); if (c >= 'a' && c <= 'z') { break; } if ((ch >= '0' && ch <= '9') || ch == '.' || ch == '-') { break; } switch (ch) { case ':': r->host_end = p; state = sw_port; break; case '/': r->host_end = p; r->uri_start = p; state = sw_after_slash_in_uri; break; default: r->host_end = p; return NGX_HTTP_PARSE_INVALID_REQUEST; } break; case sw_port: if (ch >= '0' && ch <= '9') { break; } switch (ch) { case '/': r->port_end = p; r->uri_start = p; state = sw_after_slash_in_uri; break; default: return NGX_HTTP_PARSE_INVALID_REQUEST; } break; /* check "/.", "//", "%", and "\" (Win32) in URI */ case sw_after_slash_in_uri: if (usual[ch >> 5] & (1 << (ch & 0x1f))) { state = sw_check_uri; break; } switch (ch) { case ' ': r->uri_end = p; state = sw_http_09; break; case CR: r->uri_end = p; r->http_minor = 9; state = sw_almost_done; break; case LF: r->uri_end = p; r->http_minor = 9; goto done; case '.': r->complex_uri = 1; state = sw_uri; break; case '%': r->quoted_uri = 1; state = sw_uri; break; case '/': r->complex_uri = 1; state = sw_uri; break; #if (NGX_WIN32) case '\\': r->complex_uri = 1; state = sw_uri; break; #endif case '?': r->args_start = p + 1; state = sw_uri; break; case '#': r->complex_uri = 1; state = sw_uri; break; case '+': r->plus_in_uri = 1; break; case '\0': r->zero_in_uri = 1; break; default: state = sw_check_uri; break; } break; /* check "/", "%" and "\" (Win32) in URI */ case sw_check_uri: if (usual[ch >> 5] & (1 << (ch & 0x1f))) { break; } switch (ch) { case '/': r->uri_ext = NULL; state = sw_after_slash_in_uri; break; case '.': r->uri_ext = p + 1; break; case ' ': r->uri_end = p; state = sw_http_09; break; case CR: r->uri_end = p; r->http_minor = 9; state = sw_almost_done; break; case LF: r->uri_end = p; r->http_minor = 9; goto done; #if (NGX_WIN32) case '\\': r->complex_uri = 1; state = sw_after_slash_in_uri; break; #endif case '%': r->quoted_uri = 1; state = sw_uri; break; case '?': r->args_start = p + 1; state = sw_uri; break; case '#': r->complex_uri = 1; state = sw_uri; break; case '+': r->plus_in_uri = 1; break; case '\0': r->zero_in_uri = 1; break; } break; /* URI */ case sw_uri: if (usual[ch >> 5] & (1 << (ch & 0x1f))) { break; } switch (ch) { case ' ': r->uri_end = p; state = sw_http_09; break; case CR: r->uri_end = p; r->http_minor = 9; state = sw_almost_done; break; case LF: r->uri_end = p; r->http_minor = 9; goto done; case '#': r->complex_uri = 1; break; case '\0': r->zero_in_uri = 1; break; } break; /* space+ after URI */ case sw_http_09: switch (ch) { case ' ': break; case CR: r->http_minor = 9; state = sw_almost_done; break; case LF: r->http_minor = 9; goto done; case 'H': r->http_protocol.data = p; state = sw_http_H; break; default: return NGX_HTTP_PARSE_INVALID_REQUEST; } break; case sw_http_H: switch (ch) { case 'T': state = sw_http_HT; break; default: return NGX_HTTP_PARSE_INVALID_REQUEST; } break; case sw_http_HT: switch (ch) { case 'T': state = sw_http_HTT; break; default: return NGX_HTTP_PARSE_INVALID_REQUEST; } break; case sw_http_HTT: switch (ch) { case 'P': state = sw_http_HTTP; break; default: return NGX_HTTP_PARSE_INVALID_REQUEST; } break; case sw_http_HTTP: switch (ch) { case '/': state = sw_first_major_digit; break; default: return NGX_HTTP_PARSE_INVALID_REQUEST; } break; /* first digit of major HTTP version */ case sw_first_major_digit: if (ch < '1' || ch > '9') { return NGX_HTTP_PARSE_INVALID_REQUEST; } r->http_major = ch - '0'; state = sw_major_digit; break; /* major HTTP version or dot */ case sw_major_digit: if (ch == '.') { state = sw_first_minor_digit; break; } if (ch < '0' || ch > '9') { return NGX_HTTP_PARSE_INVALID_REQUEST; } r->http_major = r->http_major * 10 + ch - '0'; break; /* first digit of minor HTTP version */ case sw_first_minor_digit: if (ch < '0' || ch > '9') { return NGX_HTTP_PARSE_INVALID_REQUEST; } r->http_minor = ch - '0'; state = sw_minor_digit; break; /* minor HTTP version or end of request line */ case sw_minor_digit: if (ch == CR) { state = sw_almost_done; break; } if (ch == LF) { goto done; } if (ch < '0' || ch > '9') { return NGX_HTTP_PARSE_INVALID_REQUEST; } r->http_minor = r->http_minor * 10 + ch - '0'; break; /* end of request line */ case sw_almost_done: r->request_end = p - 1; switch (ch) { case LF: goto done; default: return NGX_HTTP_PARSE_INVALID_REQUEST; } } } b->pos = p; r->state = state; return NGX_AGAIN; done: b->pos = p + 1; if (r->request_end == NULL) { r->request_end = p; } r->http_version = r->http_major * 1000 + r->http_minor; r->state = sw_start; if (r->http_version == 9 && r->method != NGX_HTTP_GET) { return NGX_HTTP_PARSE_INVALID_09_METHOD; } return NGX_OK; } ngx_int_t ngx_http_parse_header_line(ngx_http_request_t *r, ngx_buf_t *b) { u_char c, ch, *p; ngx_uint_t hash, i; enum { sw_start = 0, sw_name, sw_space_before_value, sw_value, sw_space_after_value, sw_ignore_line, sw_almost_done, sw_header_almost_done } state; /* the last '\0' is not needed because string is zero terminated */ static u_char lowcase[] = "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0" "\0\0\0\0\0\0\0\0\0\0\0\0\0-\0\0" "0123456789\0\0\0\0\0\0" "\0abcdefghijklmnopqrstuvwxyz\0\0\0\0\0" "\0abcdefghijklmnopqrstuvwxyz\0\0\0\0\0" "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0" "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0" "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0" "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"; state = r->state; hash = r->header_hash; i = r->lowcase_index; for (p = b->pos; p < b->last; p++) { ch = *p; switch (state) { /* first char */ case sw_start: r->invalid_header = 0; switch (ch) { case CR: r->header_end = p; state = sw_header_almost_done; break; case LF: r->header_end = p; goto header_done; default: state = sw_name; r->header_name_start = p; c = lowcase[ch]; if (c) { hash = ngx_hash(0, c); r->lowcase_header[0] = c; i = 1; break; } r->invalid_header = 1; break; } break; /* header name */ case sw_name: c = lowcase[ch]; if (c) { hash = ngx_hash(hash, c); r->lowcase_header[i++] = c; i &= ~NGX_HTTP_LC_HEADER_LEN; break; } if (ch == ':') { r->header_name_end = p; state = sw_space_before_value; break; } if (ch == CR) { r->header_name_end = p; r->header_start = p; r->header_end = p; state = sw_almost_done; break; } if (ch == LF) { r->header_name_end = p; r->header_start = p; r->header_end = p; goto done; } /* IIS may send the duplicate "HTTP/1.1 ..." lines */ if (ch == '/' && r->upstream && p - r->header_name_start == 4 && ngx_strncmp(r->header_name_start, "HTTP", 4) == 0) { state = sw_ignore_line; break; } r->invalid_header = 1; break; /* space* before header value */ case sw_space_before_value: switch (ch) { case ' ': break; case CR: r->header_start = p; r->header_end = p; state = sw_almost_done; break; case LF: r->header_start = p; r->header_end = p; goto done; default: r->header_start = p; state = sw_value; break; } break; /* header value */ case sw_value: switch (ch) { case ' ': r->header_end = p; state = sw_space_after_value; break; case CR: r->header_end = p; state = sw_almost_done; break; case LF: r->header_end = p; goto done; } break; /* space* before end of header line */ case sw_space_after_value: switch (ch) { case ' ': break; case CR: state = sw_almost_done; break; case LF: goto done; default: state = sw_value; break; } break; /* ignore header line */ case sw_ignore_line: switch (ch) { case LF: state = sw_start; break; default: break; } break; /* end of header line */ case sw_almost_done: switch (ch) { case CR: break; case LF: goto done; default: return NGX_HTTP_PARSE_INVALID_HEADER; } break; /* end of header */ case sw_header_almost_done: switch (ch) { case LF: goto header_done; default: return NGX_HTTP_PARSE_INVALID_HEADER; } } } b->pos = p; r->state = state; r->header_hash = hash; r->lowcase_index = i; return NGX_AGAIN; done: b->pos = p + 1; r->state = sw_start; r->header_hash = hash; r->lowcase_index = i; return NGX_OK; header_done: b->pos = p + 1; r->state = sw_start; return NGX_HTTP_PARSE_HEADER_DONE; } ngx_int_t ngx_http_parse_complex_uri(ngx_http_request_t *r) { u_char c, ch, decoded, *p, *u; enum { sw_usual = 0, sw_slash, sw_dot, sw_dot_dot, #if (NGX_WIN32) sw_dot_dot_dot, #endif sw_quoted, sw_quoted_second } state, quoted_state; #if (NGX_SUPPRESS_WARN) decoded = '\0'; quoted_state = sw_usual; #endif state = sw_usual; p = r->uri_start; u = r->uri.data; r->uri_ext = NULL; r->args_start = NULL; ch = *p++; while (p <= r->uri_end) { /* * we use "ch = *p++" inside the cycle, but this operation is safe, * because after the URI there is always at least one charcter: * the line feed */ ngx_log_debug4(NGX_LOG_DEBUG_HTTP, r->connection->log, 0, "s:%d in:'%Xd:%c', out:'%c'", state, ch, ch, *u); switch (state) { case sw_usual: if (usual[ch >> 5] & (1 << (ch & 0x1f))) { *u++ = ch; ch = *p++; break; } switch(ch) { #if (NGX_WIN32) case '\\': r->uri_ext = NULL; if (p == r->uri_start + r->uri.len) { /* * we omit the last "\" to cause redirect because * the browsers do not treat "\" as "/" in relative URL path */ break; } state = sw_slash; *u++ = '/'; break; #endif case '/': r->uri_ext = NULL; state = sw_slash; *u++ = ch; break; case '%': quoted_state = state; state = sw_quoted; break; case '?': r->args_start = p; goto args; case '#': goto done; case '.': r->uri_ext = u + 1; *u++ = ch; break; case '+': r->plus_in_uri = 1; default: *u++ = ch; break; } ch = *p++; break; case sw_slash: if (usual[ch >> 5] & (1 << (ch & 0x1f))) { state = sw_usual; *u++ = ch; ch = *p++; break; } switch(ch) { #if (NGX_WIN32) case '\\': #endif case '/': break; case '.': state = sw_dot; *u++ = ch; break; case '%': quoted_state = state; state = sw_quoted; break; case '?': r->args_start = p; goto args; case '#': goto done; case '+': r->plus_in_uri = 1; default: state = sw_usual; *u++ = ch; break; } ch = *p++; break; case sw_dot: if (usual[ch >> 5] & (1 << (ch & 0x1f))) { state = sw_usual; *u++ = ch; ch = *p++; break; } switch(ch) { #if (NGX_WIN32) case '\\': #endif case '/': state = sw_slash; u--; break; case '.': state = sw_dot_dot; *u++ = ch; break; case '%': quoted_state = state; state = sw_quoted; break; case '?': r->args_start = p; goto args; case '#': goto done; case '+': r->plus_in_uri = 1; default: state = sw_usual; *u++ = ch; break; } ch = *p++; break; case sw_dot_dot: if (usual[ch >> 5] & (1 << (ch & 0x1f))) { state = sw_usual; *u++ = ch; ch = *p++; break; } switch(ch) { #if (NGX_WIN32) case '\\': #endif case '/': state = sw_slash; u -= 4; if (u < r->uri.data) { return NGX_HTTP_PARSE_INVALID_REQUEST; } while (*(u - 1) != '/') { u--; } break; case '%': quoted_state = state; state = sw_quoted; break; case '?': r->args_start = p; goto args; case '#': goto done; #if (NGX_WIN32) case '.': state = sw_dot_dot_dot; *u++ = ch; break; #endif case '+': r->plus_in_uri = 1; default: state = sw_usual; *u++ = ch; break; } ch = *p++; break; #if (NGX_WIN32) case sw_dot_dot_dot: if (usual[ch >> 5] & (1 << (ch & 0x1f))) { state = sw_usual; *u++ = ch; ch = *p++; break; } switch(ch) { case '\\': case '/': state = sw_slash; u -= 5; if (u < r->uri.data) { return NGX_HTTP_PARSE_INVALID_REQUEST; } while (*u != '/') { u--; } if (u < r->uri.data) { return NGX_HTTP_PARSE_INVALID_REQUEST; } while (*(u - 1) != '/') { u--; } break; case '%': quoted_state = state; state = sw_quoted; break; case '?': r->args_start = p; goto args; case '#': goto done; case '+': r->plus_in_uri = 1; default: state = sw_usual; *u++ = ch; break; } ch = *p++; break; #endif case sw_quoted: r->quoted_uri = 1; if (ch >= '0' && ch <= '9') { decoded = (u_char) (ch - '0'); state = sw_quoted_second; ch = *p++; break; } c = (u_char) (ch | 0x20); if (c >= 'a' && c <= 'f') { decoded = (u_char) (c - 'a' + 10); state = sw_quoted_second; ch = *p++; break; } return NGX_HTTP_PARSE_INVALID_REQUEST; case sw_quoted_second: if (ch >= '0' && ch <= '9') { ch = (u_char) ((decoded << 4) + ch - '0'); if (ch == '%') { state = sw_usual; *u++ = ch; ch = *p++; break; } if (ch == '#') { *u++ = ch; ch = *p++; } else if (ch == '\0') { r->zero_in_uri = 1; } state = quoted_state; break; } c = (u_char) (ch | 0x20); if (c >= 'a' && c <= 'f') { ch = (u_char) ((decoded << 4) + c - 'a' + 10); if (ch == '?') { *u++ = ch; ch = *p++; } else if (ch == '+') { r->plus_in_uri = 1; } state = quoted_state; break; } return NGX_HTTP_PARSE_INVALID_REQUEST; } } done: r->uri.len = u - r->uri.data; if (r->uri_ext) { r->exten.len = u - r->uri_ext; r->exten.data = r->uri_ext; } r->uri_ext = NULL; return NGX_OK; args: while (p < r->uri_end) { if (*p++ != '#') { continue; } r->args.len = p - 1 - r->args_start; r->args.data = r->args_start; r->args_start = NULL; break; } r->uri.len = u - r->uri.data; if (r->uri_ext) { r->exten.len = u - r->uri_ext; r->exten.data = r->uri_ext; } r->uri_ext = NULL; return NGX_OK; } ngx_int_t ngx_http_parse_unsafe_uri(ngx_http_request_t *r, ngx_str_t *uri, ngx_str_t *args, ngx_uint_t *flags) { u_char ch, *p; size_t len; len = uri->len; p = uri->data; if (len == 0 || p[0] == '?') { goto unsafe; } if (p[0] == '.' && len == 3 && p[1] == '.' && (p[2] == '/' #if (NGX_WIN32) || p[2] == '\\' #endif )) { goto unsafe; } for ( /* void */ ; len; len--) { ch = *p++; if (usual[ch >> 5] & (1 << (ch & 0x1f))) { continue; } if (ch == '?') { args->len = len - 1; args->data = p; uri->len -= len; return NGX_OK; } if (ch == '\0') { *flags |= NGX_HTTP_ZERO_IN_URI; continue; } if ((ch == '/' #if (NGX_WIN32) || ch == '\\' #endif ) && len > 2) { /* detect "/../" */ if (p[0] == '.' && p[1] == '.' && p[2] == '/') { goto unsafe; } #if (NGX_WIN32) if (p[2] == '\\') { goto unsafe; } if (len > 3) { /* detect "/.../" */ if (p[0] == '.' && p[1] == '.' && p[2] == '.' && (p[3] == '/' || p[3] == '\\')) { goto unsafe; } } #endif } } return NGX_OK; unsafe: ngx_log_error(NGX_LOG_ERR, r->connection->log, 0, "unsafe URI \"%V\" was detected", uri); return NGX_ERROR; } ngx_int_t ngx_http_parse_multi_header_lines(ngx_array_t *headers, ngx_str_t *name, ngx_str_t *value) { ngx_uint_t i; u_char *start, *last, *end, ch; ngx_table_elt_t **h; h = headers->elts; for (i = 0; i < headers->nelts; i++) { ngx_log_debug2(NGX_LOG_DEBUG_HTTP, headers->pool->log, 0, "parse header: \"%V: %V\"", &h[i]->key, &h[i]->value); if (name->len > h[i]->value.len) { continue; } start = h[i]->value.data; end = h[i]->value.data + h[i]->value.len; while (start < end) { if (ngx_strncasecmp(start, name->data, name->len) != 0) { goto skip; } for (start += name->len; start < end && *start == ' '; start++) { /* void */ } if (value == NULL) { if (start == end || *start == ',') { return i; } goto skip; } if (start == end || *start++ != '=') { /* the invalid header value */ goto skip; } while (start < end && *start == ' ') { start++; } for (last = start; last < end && *last != ';'; last++) { /* void */ } value->len = last - start; value->data = start; return i; skip: while (start < end) { ch = *start++; if (ch == ';' || ch == ',') { break; } } while (start < end && *start == ' ') { start++; } } } return NGX_DECLINED; }