File size: 7,956 Bytes
d1ceb73
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""Read and write notebooks as regular .py files.

Authors:

* Brian Granger
"""

# -----------------------------------------------------------------------------
#  Copyright (C) 2008-2011  The IPython Development Team
#
#  Distributed under the terms of the BSD License.  The full license is in
#  the file LICENSE, distributed as part of this software.
# -----------------------------------------------------------------------------

# -----------------------------------------------------------------------------
# Imports
# -----------------------------------------------------------------------------
from __future__ import annotations

import re

from .nbbase import (
    nbformat,
    nbformat_minor,
    new_code_cell,
    new_heading_cell,
    new_notebook,
    new_text_cell,
    new_worksheet,
)
from .rwbase import NotebookReader, NotebookWriter

# -----------------------------------------------------------------------------
# Code
# -----------------------------------------------------------------------------

_encoding_declaration_re = re.compile(r"^#.*coding[:=]\s*([-\w.]+)")


class PyReaderError(Exception):
    """An error raised for a pyreader error."""


class PyReader(NotebookReader):
    """A python notebook reader."""

    def reads(self, s, **kwargs):
        """Convert a string to a notebook"""
        return self.to_notebook(s, **kwargs)

    def to_notebook(self, s, **kwargs):
        """Convert a string to a notebook"""
        lines = s.splitlines()
        cells = []
        cell_lines: list[str] = []
        kwargs = {}
        state = "codecell"
        for line in lines:
            if line.startswith("# <nbformat>") or _encoding_declaration_re.match(line):
                pass
            elif line.startswith("# <codecell>"):
                cell = self.new_cell(state, cell_lines, **kwargs)
                if cell is not None:
                    cells.append(cell)
                state = "codecell"
                cell_lines = []
                kwargs = {}
            elif line.startswith("# <htmlcell>"):
                cell = self.new_cell(state, cell_lines, **kwargs)
                if cell is not None:
                    cells.append(cell)
                state = "htmlcell"
                cell_lines = []
                kwargs = {}
            elif line.startswith("# <markdowncell>"):
                cell = self.new_cell(state, cell_lines, **kwargs)
                if cell is not None:
                    cells.append(cell)
                state = "markdowncell"
                cell_lines = []
                kwargs = {}
            # VERSIONHACK: plaintext -> raw
            elif line.startswith(("# <rawcell>", "# <plaintextcell>")):
                cell = self.new_cell(state, cell_lines, **kwargs)
                if cell is not None:
                    cells.append(cell)
                state = "rawcell"
                cell_lines = []
                kwargs = {}
            elif line.startswith("# <headingcell"):
                cell = self.new_cell(state, cell_lines, **kwargs)
                if cell is not None:
                    cells.append(cell)
                    cell_lines = []
                m = re.match(r"# <headingcell level=(?P<level>\d)>", line)
                if m is not None:
                    state = "headingcell"
                    kwargs = {}
                    kwargs["level"] = int(m.group("level"))
                else:
                    state = "codecell"
                    kwargs = {}
                    cell_lines = []
            else:
                cell_lines.append(line)
        if cell_lines and state == "codecell":
            cell = self.new_cell(state, cell_lines)
            if cell is not None:
                cells.append(cell)
        ws = new_worksheet(cells=cells)
        return new_notebook(worksheets=[ws])

    def new_cell(self, state, lines, **kwargs):
        """Create a new cell."""
        if state == "codecell":
            input_ = "\n".join(lines)
            input_ = input_.strip("\n")
            if input_:
                return new_code_cell(input=input_)
        elif state == "htmlcell":
            text = self._remove_comments(lines)
            if text:
                return new_text_cell("html", source=text)
        elif state == "markdowncell":
            text = self._remove_comments(lines)
            if text:
                return new_text_cell("markdown", source=text)
        elif state == "rawcell":
            text = self._remove_comments(lines)
            if text:
                return new_text_cell("raw", source=text)
        elif state == "headingcell":
            text = self._remove_comments(lines)
            level = kwargs.get("level", 1)
            if text:
                return new_heading_cell(source=text, level=level)

    def _remove_comments(self, lines):
        new_lines = []
        for line in lines:
            if line.startswith("#"):
                new_lines.append(line[2:])
            else:
                new_lines.append(line)
        text = "\n".join(new_lines)
        text = text.strip("\n")
        return text  # noqa: RET504

    def split_lines_into_blocks(self, lines):
        """Split lines into code blocks."""
        if len(lines) == 1:
            yield lines[0]
            raise StopIteration()
        import ast

        source = "\n".join(lines)
        code = ast.parse(source)
        starts = [x.lineno - 1 for x in code.body]
        for i in range(len(starts) - 1):
            yield "\n".join(lines[starts[i] : starts[i + 1]]).strip("\n")
        yield "\n".join(lines[starts[-1] :]).strip("\n")


class PyWriter(NotebookWriter):
    """A Python notebook writer."""

    def writes(self, nb, **kwargs):
        """Convert a notebook to a string."""
        lines = ["# -*- coding: utf-8 -*-"]
        lines.extend(
            [
                "# <nbformat>%i.%i</nbformat>" % (nbformat, nbformat_minor),
                "",
            ]
        )
        for ws in nb.worksheets:
            for cell in ws.cells:
                if cell.cell_type == "code":
                    input_ = cell.get("input")
                    if input_ is not None:
                        lines.extend(["# <codecell>", ""])
                        lines.extend(input_.splitlines())
                        lines.append("")
                elif cell.cell_type == "html":
                    input_ = cell.get("source")
                    if input_ is not None:
                        lines.extend(["# <htmlcell>", ""])
                        lines.extend(["# " + line for line in input_.splitlines()])
                        lines.append("")
                elif cell.cell_type == "markdown":
                    input_ = cell.get("source")
                    if input_ is not None:
                        lines.extend(["# <markdowncell>", ""])
                        lines.extend(["# " + line for line in input_.splitlines()])
                        lines.append("")
                elif cell.cell_type == "raw":
                    input_ = cell.get("source")
                    if input_ is not None:
                        lines.extend(["# <rawcell>", ""])
                        lines.extend(["# " + line for line in input_.splitlines()])
                        lines.append("")
                elif cell.cell_type == "heading":
                    input_ = cell.get("source")
                    level = cell.get("level", 1)
                    if input_ is not None:
                        lines.extend(["# <headingcell level=%s>" % level, ""])
                        lines.extend(["# " + line for line in input_.splitlines()])
                        lines.append("")
        lines.append("")
        return "\n".join(lines)


_reader = PyReader()
_writer = PyWriter()

reads = _reader.reads
read = _reader.read
to_notebook = _reader.to_notebook
write = _writer.write
writes = _writer.writes