In Pass 1 of the SIC/XE assembler, the primary task is to scan the assembly source code to create a symbol table that maps labels to memory addresses. It also generates an intermediate code with placeholders for addresses and detects syntax errors. Pass 1 does not produce the final machine code but prepares the necessary information for Pass 2, where the actual machine code is generated and addresses are resolved. 

The objective of Assembler Pass1:

• Read the source code line by line.

• Identify and process any assembler directives, such as the START directive, which specifies the starting address of the program.

• Identify and process any labels used in the source code. Labels are typically followed by a colon and are used to mark specific locations in the program.

• Generate the symbol table by storing the labels and their corresponding addresses or values.

• Identify and process any variables or constants used in the source code. Variables are typically allocated memory space, while constants are assigned specific values.

• Generate the intermediate code, which is a simplified representation of the source code that can be easily processed by the assembler in subsequent passes.

The first pass of an assembler converts assembly language to machine language. The second pass of an assembler reads the intermediate file, generates object code, and writes the final object program.

The data structure used in Assembler Pass1:

In terms of data structures, Pass 1 of an assembler typically uses the following:

• Symbol Table: This data structure is used to store the labels and their corresponding addresses or values. It can be implemented as a hash table, where the labels are the keys and the addresses or values are the associated values.

• Intermediate Code: This data structure is used to store the simplified representation of the source code. It can be implemented as a list or an array of data structures, where each data structure represents a line of code and contains information such as the opcode and operands.

begin

read first input line

if OPCODE ='START' then

begin

save #[OPERAND] as starting address

initialize LOCCTR to starting address

write line to intermediate file

read next input line

end {if START}

else

initialize LOCCTR to 0

while OCODE != 'END' do

begin

if this is not a comment line then

begin

if there is a symbol in the LABEL field then

begin

search SYMTAB for LABEL

if found then

set error flag (duplicate symbol)

else

insert (LABEL,LOCCTR) into SYMTAB

end {if symbol}

search OPTAB for OPCODE

if found then

add 3 {instruction length} to LOCCTR

else if OPCODE='WORD' then

add 3 to LOCCTR

else if OPCODE = 'RESW' then

add 3 * #[OPERAND] to LOCCTR

else if OPCODE = 'RESB' then

add #[OPERAND] to LOCCTR

else if OPCODE = 'BYTE' then

begin

find length of constant in bytes

add length to LOCCTR

end {if BYTE}

else

set error flag (invalid operation code)

end {if not a comment}

write line to intermediate file

read next input line

end {while not END}

write last line to intermediate file

save (LOCCTR – starting address) as program length

end {Pass 1}

input.txt - 

COPY START 1000

- +LDA ALPHA

- ADD #1

-          DIV      #2

-   STA BETA

-          SUB      #4

-          STA      GAMMA

-         +LDA   GAMMA

-        ADD     #2

-       +LDA     BETA

ALPHA BYTE C'COF'

BETA RESW 2

GAMMA RESW     2

- END 1000

optab.txt -

DIV      06

SUB 05 

CMP 03

LDA 00

STA 23

ADD 01

JNC 08

#include <stdio.h>

#include <stdlib.h>

#include <string.h>

#include <stdbool.h>

char *decimalToHex(int decimal) {

    static char hex_string[10];

    sprintf(hex_string, "%X", decimal);

    return hex_string;

}

int main() {

    printf("PASS 1\n");

    char str;

    char saved_labels[20][20];

    int saved_labels_index = 0;

    char label[20], opcode[20], operand[20];

    char optab_opcode[10], machine_code[10];

    int starting_address, location_counter;

    bool opcode_found = false;

    FILE *input_file, *optab_file, *symtab_file, *output_file;

    input_file = fopen("input.txt", "r");

    optab_file = fopen("optab.txt", "r");

    symtab_file = fopen("symtab.txt", "w+");

    output_file = fopen("intermediate.txt", "w");

    if (input_file == NULL || optab_file == NULL || symtab_file == NULL || output_file == NULL) {

        printf("Error! opening file");

        exit(1);

    } else {

        printf("All file opened successfully\n");

    }

    fscanf(input_file, "%s %s %s", label, opcode, operand);

    if (strcmp(opcode, "START") == 0) {

        starting_address = strtol(operand, NULL, 16);

        location_counter = starting_address;

    } else {

        location_counter = 0;

        starting_address = 0;

    }

    printf("\nIntermidia File:\n\n");

    fprintf(output_file, "%s\t%s\t%s\t%s\n", "-", label, opcode, operand);

    printf("%s\t%s\t%s\t%s\n", "-", label, opcode, operand);

    fscanf(input_file, "%s %s %s", label, opcode, operand);

    while (strcmp(opcode, "END") != 0) {

        if (strcmp(label, "-") != 0) {

            for (int i = 0; i < 10; i++) {

                if (strcmp(saved_labels[i], label) == 0) {

                    printf("Error! Duplicate label: %s found at line %d\n", label, i + 1);

                    exit(1);

                }

            }

            strcpy(saved_labels[saved_labels_index], label);

            saved_labels_index++;

            fprintf(symtab_file, "%s\t%s\n", label, decimalToHex(location_counter));

        }

        rewind(optab_file);

        opcode_found = false;

        fscanf(optab_file, "%s %s", optab_opcode, machine_code);

        while (!feof(optab_file)) {

            if (strcmp(optab_opcode, opcode) == 0) {

                opcode_found = true;

                break;

            }

            fscanf(optab_file, "%s %s", optab_opcode, machine_code);

        }

        fprintf(output_file, "%s\t%s\t%s\t%s\n", decimalToHex(location_counter), label, opcode, operand);

        printf("%s\t%s\t%s\t%s\n", decimalToHex(location_counter), label, opcode, operand);

        if (opcode_found) {

            location_counter += 3;

        } else if (strcmp(opcode, "BYTE") == 0) {

            location_counter += strlen(operand) - 3;

        } else if (strcmp(opcode, "RESB") == 0) {

            location_counter += atoi(operand);

        } else if (strcmp(opcode, "WORD") == 0) {

            location_counter += 3;

        } else if (strcmp(opcode, "RESW") == 0) {

            location_counter += 3 * atoi(operand);

        } else {

            printf("Error! Invalid opcode\n");

            printf("opcode: %s\n", opcode);

            exit(1);

        }

        fscanf(input_file, "%s %s %s", label, opcode, operand);

    }

    fprintf(output_file, "%s\t%s\t%s\t%s\n", decimalToHex(location_counter), label, opcode, operand);

    printf("%s\t%s\t%s\t%s\n", decimalToHex(location_counter), label, opcode, operand);

    printf("\nSize of the program: %s\n", decimalToHex(location_counter - starting_address));

        printf("\n\nThe contents of Symbol Table :\n\n");

    fclose(input_file);

    fclose(optab_file);

    fclose(symtab_file);

    fclose(output_file);

    symtab_file = fopen("symtab.txt", "r");

    str = fgetc(symtab_file);

    while (str != EOF) {

        printf("%c", str);

        str = fgetc(symtab_file);

    }

        fclose(symtab_file);

    return 0;

}