"""
* Version: 0.1.0.0.0

* Purposes:
    * Inspects the content in the PowerPoint and save them as Markdown files under a specified folder.

* System parameters:
    * sys_parameter 1: The path to the single PowerPoint file as the input.
    * sys_parameter 2: The path to the new folder where the Markdown files are going to be stored as the output.
    * sys_parameter 3: The shape name for slide title.
    * sys_parameter 4: The shape type name for slide title. 
    * sys_parameter 5 (optional): Currently, the only supported mode is `silent`.
"""

from nis import match
import sys, os, re
from pptx import Presentation

if __name__ == "__main__":

    path_to_ppt = sys.argv[1]
    path_to_new_mds = sys.argv[2]
    if len(sys.argv) > 3:
        title_shape_name = sys.argv[3].upper()
    else:
        title_shape_name = "TITLE"
    if len(sys.argv) > 4:
        title_shape_type_name = sys.argv[4].upper()
    else:
        title_shape_type_name = "PLACEHOLDER (14)"
    mode = "standard"
    if len(sys.argv) > 5:
        mode = sys.argv[5]
    prs = Presentation(path_to_ppt)

    # Slide layouts
    if mode != "silent":
        layout_idx = 0
        print("Available layouts in master:")
        for layout in prs.slide_layouts:
            print(
                "\t[" + str(layout_idx) + "]",
                layout.name,
                ", #Placeholder count in layout:",
                len(layout.placeholders),
            )
            layout_idx += 1
    slide_count = len(prs.slides)
    slide_idx = 0
    os.makedirs(path_to_new_mds)

    title_prefix = ["# "]
    bulletin_prefix = [
        "+ ",
        "  + ",
        "    + ",
        "      + ",
        "        + ",
    ]  # level 0, 1, 2, 3, 4

    for slide in prs.slides:
        slide_idx += 1
        file_name = None
        if slide_idx == 1:
            file_name = "01title.md"
        else:
            file_name = str(slide_idx).rjust(3, "0") + ".md"
        md = open(path_to_new_mds + "/" + file_name, "x")
        shape_idx = 0
        if mode != "silent":
            print("Slide", slide_idx)
            print("\tLayout:", slide.slide_layout.name)
            print("\tAvailable shapes:")
            for shape in slide.shapes:
                print(
                    "\t\t",
                    "[" + str(shape_idx) + "]",
                    "[" + str(shape.shape_type).upper() + "]",
                )
                shape_idx += 1
        shape_handling_seq = 0
        shape_text_content = []
        shape_picture_content = []
        shape_table_content = []
        shape_chart_content = []
        for shape in slide.shapes:
            try:
                print(
                    "shape type for shape[" + str(shape_handling_seq) + "]:",
                    shape.shape_type,
                )
                if shape.has_text_frame:
                    for paragraph in shape.text_frame.paragraphs:
                        print("paragraph level:", paragraph.level)
                        if (
                            "".join(paragraph.text) == None
                            or len("".join(paragraph.text)) == 0
                        ):
                            # md.write("\n")
                            shape_text_content += ["\n"]
                        else:
                            if (
                                (title_shape_name in shape.name.upper())
                                or (
                                    str(shape.shape_type)
                                    == "PLACEHOLDER (14)"  # Google slide
                                    and len(shape_text_content) == 0
                                    and paragraph.level == 0
                                )
                                or (
                                    str(shape.shape_type)
                                    == "TEXT_BOX (17)"  # Google slide
                                    and len(shape_text_content) == 0
                                    and paragraph.level == 0
                                )
                                or (
                                    str(shape.shape_type)
                                    == title_shape_type_name  # Custom
                                    and len(shape_text_content) == 0
                                    and paragraph.level == 0
                                )
                            ):
                                # md.write(
                                #     title_prefix[paragraph.level]
                                #     + "".join(paragraph.text)
                                #     + "\n"
                                # )
                                shape_text_content += [
                                    title_prefix[paragraph.level]
                                    + "".join(paragraph.text)
                                    + "\n"
                                ]
                            elif (
                                ("TEXT" in shape.name.upper())
                                or (
                                    "PLACEHOLDER"
                                    in str(shape.shape_type).upper()  # Google slide
                                    and len(shape_text_content) > 0
                                )
                                or (
                                    "TEXT_BOX"
                                    in str(shape.shape_type).upper()  # Google slide
                                    and len(shape_text_content) > 0
                                )
                            ):
                                # md.write(
                                #     bulletin_prefix[paragraph.level]
                                #     + "".join(paragraph.text)
                                #     + "\n"
                                # )
                                shape_text_content += [
                                    bulletin_prefix[paragraph.level]
                                    + "".join(paragraph.text)
                                    + "\n"
                                ]
                            else:
                                # md.write("".join(paragraph.text) + "\n")
                                shape_text_content += ["".join(paragraph.text) + "\n"]
                elif re.match("(PICTURE|图像)", str(shape.shape_type).upper()):
                    # md.write("![`smart`](place-holder.png)" + "\n\n")
                    shape_picture_content += ["![`smart`](place-holder.png)" + "\n\n"]
                elif "TABLE" in str(shape.shape_type).upper():
                    # md.write("<TABLE-PLACEHOLDER>" + "\n")
                    shape_table_content += ["<TABLE-PLACEHOLDER>" + "\n"]
                elif "CHART" in str(shape.shape_type).upper():
                    # md.write("<CHART-PLACEHOLDER>" + "\n")
                    shape_chart_content += ["<CHART-PLACEHOLDER>" + "\n"]
                else:
                    print("\t\tCannot handle this shape_type:", shape.shape_type)
            except AttributeError as ex:  # AttributeError: 'Picture' object has no attribute 'text_frame'
                print("cmd_inspect_ppt from", shape.name.upper(), ex)
            shape_handling_seq += 1
        for line in shape_text_content:
            md.write(line)
        for line in shape_table_content:
            md.write(line)
        for line in shape_chart_content:
            md.write(line)
        for line in shape_picture_content:
            md.write(line)
        md.write("-" * 60 + "\n")
        if slide.has_notes_slide:
            notes_slide = slide.notes_slide
            text_frame = notes_slide.notes_text_frame
            md.write(text_frame.text + "\n")
        md.close()
    if mode != "silent":
        print("cmd_inspect_ppt.py: Done.")