import docx, io
from docx import Document
from docx.document import Document as _Document
from docx.oxml.text.paragraph import CT_P
from docx.oxml.table import CT_Tbl
from docx.table import _Cell, Table
from docx.text.paragraph import Paragraph

def iter_block_items(parent):
    """
    Generate a reference to each paragraph and table child within *parent*,
    in document order. Each returned value is an instance of either Table or
    Paragraph. *parent* would most commonly be a reference to a main
    Document object, but also works for a _Cell object, which itself can
    contain paragraphs and tables.
    """
    if isinstance(parent, _Document):
        parent_elm = parent.element.body
        #print("Parent1 XML: ", parent_elm)
    elif isinstance(parent, _Cell):
        parent_elm = parent._tc
    else:
        raise ValueError("something's not right")

    for child in parent_elm.iterchildren():
        if isinstance(child, CT_P):
            yield Paragraph(child, parent)
        elif isinstance(child, CT_Tbl):
            yield Table(child, parent)

def get_df_row_para(num,block):
    paragraph = block
    para_text = paragraph.text.strip().strip("\n")
    return [para_text]

def get_df_row_table(num,block):
    rows = []
    table = block
    for row in table.rows:
        tpara = []
        for cell in row.cells:
            for paragraph in cell.paragraphs:
                para_text = paragraph.text.strip().strip("\n")
                tpara.append(para_text)       
        para_text = str(" ".join(tpara))
        rows.append([para_text])
        num+=1
    return num, rows

def txt_from_docx(document_,with_api=True):
    """
    document_path: path of docx file
    Return a df with all the lines in docx file
    """
    # to keep out false positives you can keep a list of rejected headings
    if not with_api:
        document = Document(io.BytesIO(document_))
    else:
        document = Document(document_)
    rows = []
    num = 1
    for block in iter_block_items(document):
        if isinstance(block, Paragraph):
            row = get_df_row_para(num,block)
            rows.extend(row)
            num = num+1
        elif isinstance(block, Table):
            num, rows_ = get_df_row_table(num,block)
            rows += rows_
    return rows