From e5cba43a0e5a19360d87594ae22cdb94872e536c Mon Sep 17 00:00:00 2001
From: Aryadev Chavali <aryadev@aryadevchavali.com>
Date: Sat, 2 Sep 2023 16:14:49 +0100
Subject: New module for parser functions

Same principle as main->lib (previous commit).
---
 Makefile |   2 +-
 main.c   | 157 +--------------------------------------------------------------
 parser.c | 144 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 parser.h |  32 +++++++++++++
 4 files changed, 178 insertions(+), 157 deletions(-)
 create mode 100644 parser.c
 create mode 100644 parser.h

diff --git a/Makefile b/Makefile
index 9e7800c..09de95d 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 CC=gcc
 CFLAGS=-Wall -Wextra -Wpedantic -ggdb -fsanitize=address -std=c11
 LIBS=
-OBJECTS=lib.o main.o
+OBJECTS=lib.o parser.o main.o
 OUT=obf.out
 ARGS=
 
diff --git a/main.c b/main.c
index dc7269a..dad7e92 100644
--- a/main.c
+++ b/main.c
@@ -11,6 +11,7 @@
 #include <string.h>
 
 #include "./lib.h"
+#include "./parser.h"
 
 #define MEMORY_DEFAULT 30000
 
@@ -20,162 +21,6 @@ typedef struct
   uint8_t memory[MEMORY_DEFAULT];
 } machine_t;
 
-typedef struct AST
-{
-  size_t col, row;
-  enum
-  {
-    NEXT = 0,
-    PREV,
-    INC,
-    DEC,
-    OUT,
-    READ,
-    LIN,
-    LOUT
-  } type;
-  int loop_ref;
-} node_t;
-
-char *ast_to_str(node_t *ast, size_t size)
-{
-  char *out = calloc(size + 1, 1);
-  for (size_t i = 0; i < size; ++i)
-  {
-    switch (ast[i].type)
-    {
-    case NEXT:
-      out[i] = '>';
-      break;
-    case PREV:
-      out[i] = '<';
-      break;
-    case INC:
-      out[i] = '+';
-      break;
-    case DEC:
-      out[i] = '-';
-      break;
-    case OUT:
-      out[i] = '.';
-      break;
-    case READ:
-      out[i] = ',';
-      break;
-    case LIN:
-      out[i] = '[';
-      break;
-    case LOUT:
-      out[i] = ']';
-      break;
-    }
-  }
-  out[size] = '\0';
-  return out;
-}
-
-struct PResult
-{
-  node_t *nodes;
-  size_t size;
-} parse_buffer(buffer_t *buffer)
-{
-  node_t *nodes = NULL;
-  size_t usable = 0, loops = 0;
-  for (size_t i = 0; i < buffer->size; ++i)
-    if (usable_character(buffer->data[i]))
-    {
-      ++usable;
-      if (buffer->data[i] == '[')
-        ++loops;
-    }
-  nodes = calloc(usable, sizeof(*nodes));
-
-  // First pass: Get my info
-  for (size_t i = 0, col = 0, row = 1, nptr = 0; i < buffer->size; ++i)
-  {
-    ++col;
-    if (buffer->data[i] == '\n')
-    {
-      ++row;
-      col = 0;
-    }
-    else if (usable_character(buffer->data[i]))
-    {
-      nodes[nptr].col = col;
-      nodes[nptr].row = row;
-      switch (buffer->data[i])
-      {
-      case '>':
-        nodes[nptr].type = NEXT;
-        break;
-      case '<':
-        nodes[nptr].type = PREV;
-        break;
-      case '+':
-        nodes[nptr].type = INC;
-        break;
-      case '-':
-        nodes[nptr].type = DEC;
-        break;
-      case '.':
-        nodes[nptr].type = OUT;
-        break;
-      case ',':
-        nodes[nptr].type = READ;
-        break;
-      case '[':
-        nodes[nptr].type     = LIN;
-        nodes[nptr].loop_ref = -1;
-        break;
-      case ']':
-        nodes[nptr].type     = LOUT;
-        nodes[nptr].loop_ref = -1;
-        break;
-      }
-      ++nptr;
-    }
-  }
-
-  // Second pass: setup any loop references
-  node_t *stack[loops];
-  memset(stack, 0, loops);
-  size_t stackptr = 0;
-  for (size_t i = 0; i < usable; ++i)
-  {
-    node_t *node = nodes + i;
-    if (node->type == LIN)
-      stack[stackptr++] = node;
-    else if (node->type == LOUT)
-    {
-      if (stackptr == 0)
-      {
-        print_error(buffer->name, node->row, node->col,
-                    "ERROR: Unbalanced square brackets!");
-        goto error;
-      }
-      // Access last IN loop
-      --stackptr;
-      node->loop_ref            = stack[stackptr] - nodes;
-      stack[stackptr]->loop_ref = i;
-    }
-  }
-
-  if (stackptr > 0)
-  {
-    node_t *node = nodes + usable - 1;
-    print_error(buffer->name, node->row, node->col,
-                "ERROR: Unbalanced square brackets!");
-    goto error;
-  }
-
-  return (struct PResult){nodes, usable};
-error:
-  if (nodes)
-    free(nodes);
-  return (struct PResult){0};
-}
-
 int main(int argc, char *argv[])
 {
   if (argc == 1)
diff --git a/parser.c b/parser.c
new file mode 100644
index 0000000..d1bc9c9
--- /dev/null
+++ b/parser.c
@@ -0,0 +1,144 @@
+/* parser.c
+ * Created: 2023-09-02
+ * Author: Aryadev Chavali
+ * Description: Functions for (de)serialising
+ */
+
+#include <string.h>
+
+#include "./parser.h"
+
+char *ast_to_str(node_t *ast, size_t size)
+{
+  char *out = calloc(size + 1, 1);
+  for (size_t i = 0; i < size; ++i)
+  {
+    switch (ast[i].type)
+    {
+    case NEXT:
+      out[i] = '>';
+      break;
+    case PREV:
+      out[i] = '<';
+      break;
+    case INC:
+      out[i] = '+';
+      break;
+    case DEC:
+      out[i] = '-';
+      break;
+    case OUT:
+      out[i] = '.';
+      break;
+    case READ:
+      out[i] = ',';
+      break;
+    case LIN:
+      out[i] = '[';
+      break;
+    case LOUT:
+      out[i] = ']';
+      break;
+    }
+  }
+  out[size] = '\0';
+  return out;
+}
+
+struct PResult parse_buffer(buffer_t *buffer)
+{
+  node_t *nodes = NULL;
+  size_t usable = 0, loops = 0;
+  for (size_t i = 0; i < buffer->size; ++i)
+    if (usable_character(buffer->data[i]))
+    {
+      ++usable;
+      if (buffer->data[i] == '[')
+        ++loops;
+    }
+  nodes = calloc(usable, sizeof(*nodes));
+
+  // First pass: Get my info
+  for (size_t i = 0, col = 0, row = 1, nptr = 0; i < buffer->size; ++i)
+  {
+    ++col;
+    if (buffer->data[i] == '\n')
+    {
+      ++row;
+      col = 0;
+    }
+    else if (usable_character(buffer->data[i]))
+    {
+      nodes[nptr].col = col;
+      nodes[nptr].row = row;
+      switch (buffer->data[i])
+      {
+      case '>':
+        nodes[nptr].type = NEXT;
+        break;
+      case '<':
+        nodes[nptr].type = PREV;
+        break;
+      case '+':
+        nodes[nptr].type = INC;
+        break;
+      case '-':
+        nodes[nptr].type = DEC;
+        break;
+      case '.':
+        nodes[nptr].type = OUT;
+        break;
+      case ',':
+        nodes[nptr].type = READ;
+        break;
+      case '[':
+        nodes[nptr].type     = LIN;
+        nodes[nptr].loop_ref = -1;
+        break;
+      case ']':
+        nodes[nptr].type     = LOUT;
+        nodes[nptr].loop_ref = -1;
+        break;
+      }
+      ++nptr;
+    }
+  }
+
+  // Second pass: setup any loop references
+  node_t *stack[loops];
+  memset(stack, 0, loops);
+  size_t stackptr = 0;
+  for (size_t i = 0; i < usable; ++i)
+  {
+    node_t *node = nodes + i;
+    if (node->type == LIN)
+      stack[stackptr++] = node;
+    else if (node->type == LOUT)
+    {
+      if (stackptr == 0)
+      {
+        print_error(buffer->name, node->row, node->col,
+                    "ERROR: Unbalanced square brackets!");
+        goto error;
+      }
+      // Access last IN loop
+      --stackptr;
+      node->loop_ref            = stack[stackptr] - nodes;
+      stack[stackptr]->loop_ref = i;
+    }
+  }
+
+  if (stackptr > 0)
+  {
+    node_t *node = nodes + usable - 1;
+    print_error(buffer->name, node->row, node->col,
+                "ERROR: Unbalanced square brackets!");
+    goto error;
+  }
+
+  return (struct PResult){nodes, usable};
+error:
+  if (nodes)
+    free(nodes);
+  return (struct PResult){0};
+}
diff --git a/parser.h b/parser.h
new file mode 100644
index 0000000..70ed4ff
--- /dev/null
+++ b/parser.h
@@ -0,0 +1,32 @@
+#ifndef PARSER_H
+#define PARSER_H
+
+#include "./lib.h"
+
+typedef struct AST
+{
+  size_t col, row;
+  enum
+  {
+    NEXT = 0,
+    PREV,
+    INC,
+    DEC,
+    OUT,
+    READ,
+    LIN,
+    LOUT
+  } type;
+  int loop_ref;
+} node_t;
+
+struct PResult
+{
+  node_t *nodes;
+  size_t size;
+};
+
+char *ast_to_str(node_t *ast, size_t size);
+struct PResult parse_buffer(buffer_t *buffer);
+
+#endif
-- 
cgit v1.2.3-13-gbd6f