Add support for FileXOR statements

.gitignore

@@ -2,7 +2,7 @@
 /lib
 /regression_tests/work_dirs
 
-/tree-sitter-quickbms/test/corpus/crc_scan.bms
+/tree-sitter-quickbms/test/corpus/misc_scripts
 
 # Files generate by antlr
 .antlr/

README.md

@@ -56,7 +56,7 @@ The following QuickBMS commands are currently supported by the langauge server.
 * [x] `ReverseLong VAR [ENDIAN]`
 * [x] `ReverseLongLong VAR [ENDIAN]`
 * [x] `Endian TYPE [VAR]`
-* [ ] `FileXOR SEQ [OFFSET] [FILENUM]`
+* [x] `FileXOR SEQ [OFFSET] [FILENUM]`
 * [ ] `FileRot SEQ [OFFSET] [FILENUM]`
 * [ ] `FileCrypt SEQ [OFFSET] [FILENUM]`
 * [ ] `Strlen VAR VAR [SIZE]`

src/server/keyword_docs/filexor.txt

@@ -0,0 +1,52 @@
+FileXOR SEQ [OFFSET] [FILENUM]
+
+    Any read operation (Get, *Log and so on) on any file will
+    also perform the XORing of the read data with the numbers
+    contained in the given string or in the given variable.
+    The OFFSET field by default is zero which means that if the
+    data must be xored with more than one byte (a "xor key") the
+    first byte of the key is the first byte at OFFSET which is 0
+    by default (beginning of the file).
+    Recap: the FileXOR command works with ANY file access.
+
+    Arguments:
+      SEQ       Sequence of space-separated 8bit numbers, like:
+                - asequence of bytes separated by space like 0x12
+                  or "0x12 0x34 0x56" or directly a C hex string
+                  like "\x12\x34\x56" (NOT a C notation!)
+                - a numeric variable like MYXORKEY
+                - a string not starting with numbers, '\' or '-'
+                Currently it's not possible to use a key in string
+                mode and use the Encryption command for doing it,
+                so if you have a string convert it to a numeric
+                sequence first or be sure that it doesn't start
+                with the chars shown above.
+                Set it to 0 or "" for disabling the xor.
+                Note that SEQ can be also a 32bit signed number
+                like filexor 0x11223344 but the size is decided by
+                value so 0x00000022 is 8 bit and not 32, while
+                -0x20 is considered 8bit and 0x80112233 a 32bit.
+      OFFSET    Needed only for the xor key offset.
+                If the archive is xored with a xor key from its
+                beginning (so first byte of the archive xored with
+                the first one of the key) this argument is usually
+                not necessary
+                Instead if only the file to extract is xored, this
+                argument must have the same offset of the file (so
+                just reuse the same OFFSET used in Log)
+      FILENUM   By default FileXOR is applied to ALL the files and
+                OFFSET (if specified) is referred to file 0.
+                When FILENUM is specified, it will only be applied
+                to that specific file.
+
+    Examples:
+      filexor 0xff
+      filexor -0x20
+      filexor 0x1122    # 32bit
+      filexor -0x1122   # 32bit
+      filexor "0x12 0x34 123 255"
+      filexor MYXORBYTE
+      saepos OFFSET
+      filexor "0x12 0x34 123 255" OFFSET
+      filexor "\x12\x34\x7b\xff"
+      Log NAME OFFSET SIZE

src/server/state.rs

@@ -452,6 +452,10 @@ pub fn get_keyword_docs() -> HashMap<String, String> {
             "reverselonglong".to_string(),
             include_str!("keyword_docs/reverselonglong.txt").to_string(),
         ),
+        (
+            "filexor".to_string(),
+            include_str!("keyword_docs/filexor.txt").to_string(),
+        ),
     ]
     .iter()
     .cloned()

tree-sitter-quickbms/grammar.js

@@ -41,6 +41,7 @@ module.exports = grammar({
       $.reverseshort_statement,
       $.reverselong_statement,
       $.reverselonglong_statement,
+      $.filexor_statement,
     ),
     set_statement: $ => seq(
       $.set,
@@ -213,6 +214,12 @@ module.exports = grammar({
       field("variable", $._expression),
       field("endian", optional($._endian_type)),
     ),
+    filexor_statement: $ => seq(
+      $.filexor,
+      field("sequence", $._expression),
+      field("offset", optional($._expression)),
+      // field("file_number", optional($._expression)),
+    ),
     comparison: $ => choice(
       "<",
       ">",
@@ -321,6 +328,7 @@ module.exports = grammar({
     reverseshort: $ => /[Rr][Ee][Vv][Ee][Rr][Ss][Ee][Ss][Hh][Oo][Rr][Tt]/,
     reverselong: $ => /[Rr][Ee][Vv][Ee][Rr][Ss][Ee][Ll][Oo][Nn][Gg]/,
     reverselonglong: $ => /[Rr][Ee][Vv][Ee][Rr][Ss][Ee][Ll][Oo][Nn][Gg][Ll][Oo][Nn][Gg]/,
+    filexor: $ => /[Ff][Ii][Ll][Ee][Xx][Oo][Rr]/,
     question_mark: $ => /\?/,
 
     identifier: $ => /[a-zA-Z_\\]+[a-zA-Z0-9_\-\\]*/,

tree-sitter-quickbms/test/corpus/filexor.bms

@@ -0,0 +1,51 @@
+================================================================================
+FileXOR statements
+================================================================================
+
+filexor 0xff
+filexor -0x20
+filexor 0x1122    # 32bit
+filexor -0x1122   # 32bit
+filexor "0x12 0x34 123 255"
+filexor MYXORBYTE
+# saepos OFFSET # Is this a valid command?
+filexor "0x12 0x34 123 255" OFFSET
+filexor "\x12\x34\x7b\xff"
+Log NAME OFFSET SIZE
+
+--------------------------------------------------------------------------------
+
+(source_file
+  (filexor_statement
+    (filexor)
+    (integer_literal))
+  (filexor_statement
+    (filexor)
+    (integer_literal))
+  (filexor_statement
+    (filexor)
+    (integer_literal))
+  (comment)
+  (filexor_statement
+    (filexor)
+    (integer_literal))
+  (comment)
+  (filexor_statement
+    (filexor)
+    (string_literal))
+  (filexor_statement
+    (filexor)
+    (identifier))
+  (comment)
+  (filexor_statement
+    (filexor)
+    (string_literal)
+    (identifier))
+  (filexor_statement
+    (filexor)
+    (string_literal))
+  (log_statement
+    (log)
+    (identifier)
+    (identifier)
+    (identifier)))