Implement READFILE function (#1759)

man/rgbasm.5

@@ -599,6 +599,7 @@ with its corresponding argument in
 .Pq So %% Sc is replaced by the So % Sc character .
 .It Fn STRCHAR str idx Ta Returns the substring of Ar str No for the charmap entry at Ar idx No with the current charmap . Pq Ar idx No counts charmap entries, not characters.
 .It Fn REVCHAR vals... Ta Returns the string that is mapped to Ar vals No with the current charmap. If there is no unique charmap entry for Ar vals Ns , an error occurs.
+.It Fn READFILE name max Ta Returns the contents of the file Ar name No as a string. Reads up to Ar max No bytes, or the entire contents if Ar max No is not specified. If the file isn't found in the current directory, the include-path list passed to Xr rgbasm 1 Ap s Fl I No option on the command line will be searched.
 .El
 .Pp
 The following functions operate on string expressions, but return integers.
@@ -1814,10 +1815,9 @@ Use
 .Ic INCBIN
 to include a raw binary file as it is.
 If the file isn't found in the current directory, the include-path list passed to
-.Xr rgbasm 1
+.Xr rgbasm 1 Ap s
-(see the
 .Fl I
-option) on the command line will be searched.
+option on the command line will be searched.
 .Bd -literal -offset indent
 INCBIN "titlepic.bin"
 INCBIN "sprites/hero.bin"
@@ -2370,11 +2370,10 @@ block, all of them but the first one are ignored.
 Use
 .Ic INCLUDE
 to process another assembler file and then return to the current file when done.
-If the file isn't found in the current directory, the include path list (see the
+If the file isn't found in the current directory, the include-path list passed to
+.Xr rgbasm 1 Ap s
 .Fl I
-option in
+option on the command line will be searched.
-.Xr rgbasm 1 )
-will be searched.
 You may nest
 .Ic INCLUDE
 calls infinitely (or until you run out of memory, whichever comes first).

src/asm/lexer.cpp

@@ -239,6 +239,7 @@ static std::unordered_map<std::string, int, CaseInsensitive, CaseInsensitive> ke
     {"TZCOUNT",       T_(OP_TZCOUNT)       },
 
     {"BYTELEN",       T_(OP_BYTELEN)       },
+    {"READFILE",      T_(OP_READFILE)      },
     {"STRBYTE",       T_(OP_STRBYTE)       },
     {"STRCAT",        T_(OP_STRCAT)        },
     {"STRCHAR",       T_(OP_STRCHAR)       },

src/asm/parser.y

@@ -38,6 +38,7 @@
 	#include <algorithm>
 	#include <ctype.h>
 	#include <inttypes.h>
+	#include <optional>
 	#include <stdio.h>
 	#include <stdlib.h>
 	#include <string.h>
@@ -61,6 +62,7 @@
 
 	yy::parser::symbol_type yylex(); // Provided by lexer.cpp
 
+	static std::optional<std::string> readFile(std::string const &name, uint32_t maxLen);
 	static uint32_t strToNum(std::vector<int32_t> const &s);
 	static void errorInvalidUTF8Byte(uint8_t byte, char const *functionName);
 	static size_t strlenUTF8(std::string const &str, bool printErrors);
@@ -303,6 +305,7 @@
 %token OP_LOG "LOG"
 %token OP_LOW "LOW"
 %token OP_POW "POW"
+%token OP_READFILE "READFILE"
 %token OP_REVCHAR "REVCHAR"
 %token OP_ROUND "ROUND"
 %token OP_SIN "SIN"
@@ -1687,6 +1690,20 @@ string_literal:
 		$$ = std::move($1);
 		$$.append($3);
 	}
+	| OP_READFILE LPAREN string RPAREN {
+		if (std::optional<std::string> contents = readFile($3, UINT32_MAX); contents) {
+			$$ = std::move(*contents);
+		} else {
+			YYACCEPT;
+		}
+	}
+	| OP_READFILE LPAREN string COMMA uconst RPAREN {
+		if (std::optional<std::string> contents = readFile($3, $5); contents) {
+			$$ = std::move(*contents);
+		} else {
+			YYACCEPT;
+		}
+	}
 	| OP_STRSLICE LPAREN string COMMA iconst COMMA iconst RPAREN {
 		size_t len = strlenUTF8($3, false);
 		uint32_t start = adjustNegativeIndex($5, len, "STRSLICE");
@@ -2728,6 +2745,44 @@ void yy::parser::error(std::string const &str) {
 	::error("%s", str.c_str());
 }
 
+static std::optional<std::string> readFile(std::string const &name, uint32_t maxLen) {
+	FILE *file = nullptr;
+	if (std::optional<std::string> fullPath = fstk_FindFile(name); fullPath) {
+		file = fopen(fullPath->c_str(), "rb");
+	}
+	if (!file) {
+		if (fstk_FileError(name, "READFILE")) {
+			// If `fstk_FileError` returned true due to `-MG`, we should abort due to a
+			// missing file, so return `std::nullopt`, which tells the caller to `YYACCEPT`
+			return std::nullopt;
+		}
+		return "";
+	}
+	Defer closeFile{[&] { fclose(file); }};
+
+	size_t readSize = maxLen;
+	if (fseek(file, 0, SEEK_END) == 0) {
+		// If the file is seekable and shorter than the max length,
+		// just read as many bytes as there are
+		if (long fileSize = ftell(file); static_cast<size_t>(fileSize) < readSize) {
+			readSize = fileSize;
+		}
+		fseek(file, 0, SEEK_SET);
+	} else if (errno != ESPIPE) {
+		error("Error determining size of READFILE file '%s': %s", name.c_str(), strerror(errno));
+	}
+
+	std::string contents;
+	contents.resize(readSize);
+
+	if (fread(&contents[0], 1, readSize, file) < readSize || ferror(file)) {
+		error("Error reading READFILE file '%s': %s", name.c_str(), strerror(errno));
+		return "";
+	}
+
+	return contents;
+}
+
 static uint32_t strToNum(std::vector<int32_t> const &s) {
 	uint32_t length = s.size();
 

src/asm/section.cpp

@@ -888,7 +888,7 @@ bool sect_BinaryFile(std::string const &name, uint32_t startPos) {
 	}
 	Defer closeFile{[&] { fclose(file); }};
 
-	if (fseek(file, 0, SEEK_END) != -1) {
+	if (fseek(file, 0, SEEK_END) == 0) {
 		if (startPos > ftell(file)) {
 			error("Specified start position is greater than length of file '%s'", name.c_str());
 			return false;
@@ -935,7 +935,7 @@ bool sect_BinaryFileSlice(std::string const &name, uint32_t startPos, uint32_t l
 	}
 	Defer closeFile{[&] { fclose(file); }};
 
-	if (fseek(file, 0, SEEK_END) != -1) {
+	if (fseek(file, 0, SEEK_END) == 0) {
 		if (long fsize = ftell(file); startPos > fsize) {
 			error("Specified start position is greater than length of file '%s'", name.c_str());
 			return false;

test/asm/readfile-binary.asm

@@ -0,0 +1,24 @@
+section "tilemap", rom0
+/*
+input:
+$20
+$01 $03 $05 $07 $09
+$02 $04 $06 $08 $10
+$00 $de $01 $df $80
+5
+*/
+def tilemap equs readfile("readfile-binary.inc.bin")
+def area = bytelen(#tilemap) - 2
+def offset = strbyte(#tilemap, 0)
+def width = strbyte(#tilemap, area + 1)
+db width, area / width
+for idx, area
+  db strbyte(#tilemap, idx + 1) + offset
+endr
+/*
+output:
+5, 3
+$21 $23 $25 $27 $29
+$22 $24 $26 $28 $30
+$20 $fe $21 $ff $a0
+*/

test/asm/readfile-binary.out.bin

@@ -0,0 +1 @@
+!#%')"$&(0 <20>!<21><>

test/asm/readfile-nonexist.asm

@@ -0,0 +1,2 @@
+def s equs readfile("readfile-nonexist.inc")
+assert strlen(#s) == 0

test/asm/readfile-nonexist.err

@@ -0,0 +1,3 @@
+error: readfile-nonexist.asm(1):
+    Error opening READFILE file 'readfile-nonexist.inc': No such file or directory
+Assembly aborted with 1 error!

test/asm/readfile.asm

@@ -0,0 +1,5 @@
+def s equs readfile("readfile.inc")
+println strupr(#s) ++ "!"
+
+redef s equs readfile("readfile.inc", 5)
+println strrpl(#s, "l", "w") ++ "?"

test/asm/readfile.inc

@@ -0,0 +1 @@
+hello world

test/asm/readfile.out

@@ -0,0 +1,2 @@
+HELLO WORLD!
+hewwo?