File size: 7,458 Bytes
ae312d0
94d93d2
ae312d0
94d93d2
07115d9
ae312d0
3e68ccf
 
 
 
c0b5a2b
3e68ccf
c6643c7
3e68ccf
e55d16a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3e68ccf
aa4f694
 
 
 
 
3e68ccf
 
c6643c7
 
 
 
 
 
3e68ccf
 
 
 
 
 
 
c0b5a2b
 
 
 
94d93d2
c0b5a2b
3e68ccf
 
 
ae312d0
 
3e68ccf
c0b5a2b
94d93d2
c6643c7
3e68ccf
 
 
 
 
 
 
ae312d0
3e68ccf
 
 
 
 
ae312d0
 
 
 
c0b5a2b
3e68ccf
 
 
 
 
 
 
ae312d0
3e68ccf
c6643c7
3e68ccf
c0b5a2b
 
 
 
3e68ccf
 
 
 
 
 
 
 
 
 
c6643c7
3e68ccf
 
07115d9
 
 
 
 
 
 
 
 
 
3e68ccf
 
 
 
 
 
 
94d93d2
3e68ccf
c6643c7
 
3e68ccf
07115d9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3e68ccf
07115d9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
94d93d2
 
 
 
3e68ccf
07115d9
3e68ccf
94d93d2
07115d9
3e68ccf
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
import logging
import pathlib
import re
import tempfile
from typing import List, Tuple

import json5
import pptx
import yaml

from global_config import GlobalConfig


PATTERN = re.compile(r"^slide[ ]+\d+:", re.IGNORECASE)
SAMPLE_JSON_FOR_PPTX = '''
{
    "title": "Understanding AI",
    "slides": [
        {
            "heading": "Introduction",
            "bullet_points": [
                "Brief overview of AI",
                [
                    "Importance of understanding AI"
                ]
            ]
        }
    ]
}
'''

logging.basicConfig(
    level=GlobalConfig.LOG_LEVEL,
    format='%(asctime)s - %(message)s',
)


def remove_slide_number_from_heading(header: str) -> str:
    """
    Remove the slide number from a given slide header.

    :param header: The header of a slide
    """

    if PATTERN.match(header):
        idx = header.find(':')
        header = header[idx + 1:]

    return header


def generate_powerpoint_presentation(
        structured_data: str,
        as_yaml: bool,
        slides_template: str,
        output_file_path: pathlib.Path
) -> List:
    """
    Create and save a PowerPoint presentation file containing the contents in JSON or YAML format.

    :param structured_data: The presentation contents as "JSON" (may contain trailing commas) or
    YAML
    :param as_yaml: True if the input data is in YAML format; False if it is in JSON format
    :param slides_template: The PPTX template to use
    :param output_file_path: The path of the PPTX file to save as
    :return A list of presentation title and slides headers
    """

    if as_yaml:
        # Avoid YAML mode: nested bullets can lead to incorrect YAML generation
        try:
            parsed_data = yaml.safe_load(structured_data)
        except yaml.parser.ParserError as ype:
            logging.error('*** YAML parse error: %s', str(ype))
            parsed_data = {'title': '', 'slides': []}
    else:
        # The structured "JSON" might contain trailing commas, so using json5
        parsed_data = json5.loads(structured_data)

    logging.debug(
        "*** Using PPTX template: %s",
        GlobalConfig.PPTX_TEMPLATE_FILES[slides_template]['file']
    )
    presentation = pptx.Presentation(GlobalConfig.PPTX_TEMPLATE_FILES[slides_template]['file'])

    # The title slide
    title_slide_layout = presentation.slide_layouts[0]
    slide = presentation.slides.add_slide(title_slide_layout)
    title = slide.shapes.title
    subtitle = slide.placeholders[1]
    title.text = parsed_data['title']
    logging.debug('Presentation title is: %s', title.text)
    subtitle.text = 'by Myself and SlideDeck AI :)'
    all_headers = [title.text, ]

    # background = slide.background
    # background.fill.solid()
    # background.fill.fore_color.rgb = RGBColor.from_string('C0C0C0')  # Silver
    # title.text_frame.paragraphs[0].font.color.rgb = RGBColor(0, 0, 128)  # Navy blue

    # Add contents in a loop
    for a_slide in parsed_data['slides']:
        bullet_slide_layout = presentation.slide_layouts[1]
        slide = presentation.slides.add_slide(bullet_slide_layout)
        shapes = slide.shapes

        title_shape = shapes.title
        body_shape = shapes.placeholders[1]
        title_shape.text = remove_slide_number_from_heading(a_slide['heading'])
        all_headers.append(title_shape.text)
        text_frame = body_shape.text_frame

        # The bullet_points may contain a nested hierarchy of JSON arrays
        # In some scenarios, it may contain objects (dictionaries) because the LLM generated so
        #  ^ The second scenario is not covered

        flat_items_list = get_flat_list_of_contents(a_slide['bullet_points'], level=0)

        for an_item in flat_items_list:
            paragraph = text_frame.add_paragraph()
            paragraph.text = an_item[0]
            paragraph.level = an_item[1]

    # The thank-you slide
    last_slide_layout = presentation.slide_layouts[0]
    slide = presentation.slides.add_slide(last_slide_layout)
    title = slide.shapes.title
    title.text = 'Thank you!'

    presentation.save(output_file_path)

    return all_headers


def get_flat_list_of_contents(items: list, level: int) -> List[Tuple]:
    """
    Flatten a (hierarchical) list of bullet points to a single list containing each item and its level.

    :param items: A bullet point (string or list)
    :param level: The current level of hierarchy
    :return: A list of (bullet item text, hierarchical level) tuples
    """

    flat_list = []

    for item in items:
        if isinstance(item, str):
            flat_list.append((item, level))
        elif isinstance(item, list):
            flat_list = flat_list + get_flat_list_of_contents(item, level + 1)

    return flat_list


if __name__ == '__main__':
    # bullets = [
    #     'Description',
    #     'Types',
    #     [
    #         'Type A',
    #         'Type B'
    #     ],
    #     'Grand parent',
    #     [
    #         'Parent',
    #         [
    #             'Grand child'
    #         ]
    #     ]
    # ]

    # output = get_flat_list_of_contents(bullets, level=0)
    # for x in output:
    #     print(x)

    json_data = '''
    {
    "title": "Understanding AI",
    "slides": [
        {
            "heading": "Introduction",
            "bullet_points": [
                "Brief overview of AI",
                [
                    "Importance of understanding AI"
                ]
            ]
        },
        {
            "heading": "What is AI?",
            "bullet_points": [
                "Definition of AI",
                [
                    "Types of AI",
                    [
                        "Narrow or weak AI",
                        "General or strong AI"
                    ]
                ],
                "Differences between AI and machine learning"
            ]
        },
        {
            "heading": "How AI Works",
            "bullet_points": [
                "Overview of AI algorithms",
                [
                    "Types of AI algorithms",
                    [
                        "Rule-based systems",
                        "Decision tree systems",
                        "Neural networks"
                    ]
                ],
                "How AI processes data"
            ]
        },
        {
            "heading": "Pros of AI",
            "bullet_points": [
                "Increased efficiency and productivity",
                "Improved accuracy and precision",
                "Enhanced decision-making capabilities",
                "Personalized experiences"
            ]
        },
        {
            "heading": "Cons of AI",
            "bullet_points": [
                "Job displacement and loss of employment",
                "Bias and discrimination",
                "Privacy and security concerns",
                "Dependence on technology"
            ]
        },
        {
            "heading": "Future Prospects of AI",
            "bullet_points": [
                "Advancements in fields such as healthcare and finance",
                "Increased use"
            ]
        }
    ]
}'''

    temp = tempfile.NamedTemporaryFile(delete=False, suffix='.pptx')
    path = pathlib.Path(temp.name)

    generate_powerpoint_presentation(
        json5.loads(json_data),
        as_yaml=False,
        output_file_path=path,
        slides_template='Blank'
    )