dta.py

METADATA_START = 0xd000

# Extracts the DTA as raw text from the CONfile specified in "filepath"
# Like everything else in this script, it's probably a terrible way of
# doing it but it functions well enough.
def read_metadata(filepath):
    with open(filepath, "rb") as f:
        f.seek(METADATA_START)

        metadata = []

        byte = f.read(1)

        while byte != '\x00':
            metadata.append(byte)
            byte = f.read(1)
 
    return ''.join(metadata)
                

# This will parse in the DTA file as a single text string.
# raw_string is the text of the DTA file.
# tree at first should be an empty list that you can access later
# i is the tree level (start with 0)
# Ex: parse_metadata(dta_text, tree, 0)
def parse_metadata(raw_text, tree, i):
    s = '' # Temp value to get string to add to tree.
    read_active = False

    # Shift to first opening paren
    while raw_text[i] != '(':
        i = i + 1

    i = i + 1

    # Do this until the matching close paren is found
    while raw_text[i] != ')':
        # Elements can have single or double quotation marks
        if raw_text[i] == '\'':
            i = i + 1
            while raw_text[i] != '\'':
                s = s + raw_text[i]
                i = i + 1
            tree.append(s)
            s = ''
        elif raw_text[i] == '\"':
            i = i + 1
            while raw_text[i] != '\"':
                s = s + raw_text[i]
                i = i + 1
            tree.append(s)
            s = ''
        # C3 Magma exclusive extra metadata
        elif raw_text[i] == ';':
            i = i + 1
            while raw_text[i] in ('\n', '\n'):
                s = s + raw_text[i]
                i = i + 1
            tree.append(s)
            s = ''
        # Internal subsection, start parsing recursively
        elif raw_text[i] == '(':
            subtree = []
            i = parse_metadata(raw_text, subtree, i)
            tree.append(subtree)
        # Grabs the extra shit
        elif not raw_text[i].isspace() and not read_active:
            s = s + raw_text[i]
            read_active = True
        elif not raw_text[i].isspace() and read_active:
            s = s + raw_text[i]
        elif raw_text[i].isspace and read_active:
            tree.append(s)
            s = ''
            read_active = False
        i = i + 1

    if read_active:
        tree.append(s)

    return i