python3-nbconvert 5.3.1-1 / usr / lib / python3 / dist-packages / nbconvert / nbconvertapp.py

#!/usr/bin/env python
"""NbConvert is a utility for conversion of .ipynb files.

Command-line interface for the NbConvert conversion utility.
"""

# Copyright (c) IPython Development Team.
# Distributed under the terms of the Modified BSD License.

from __future__ import print_function

import logging
import sys
import os
import glob

from jupyter_core.application import JupyterApp, base_aliases, base_flags
from traitlets.config import catch_config_error, Configurable
from traitlets import (
    Unicode, List, Instance, DottedObjectName, Type, Bool,
    default, observe,
)

from traitlets.utils.importstring import import_item

from .exporters.base import get_export_names, get_exporter
from nbconvert import exporters, preprocessors, writers, postprocessors, __version__
from .utils.base import NbConvertBase
from .utils.exceptions import ConversionException
from .utils.io import unicode_stdin_stream

#-----------------------------------------------------------------------------
#Classes and functions
#-----------------------------------------------------------------------------

class DottedOrNone(DottedObjectName):
    """A string holding a valid dotted object name in Python, such as A.b3._c
    Also allows for None type.
    """
    default_value = u''

    def validate(self, obj, value):
        if value is not None and len(value) > 0:
            return super(DottedOrNone, self).validate(obj, value)
        else:
            return value
            
nbconvert_aliases = {}
nbconvert_aliases.update(base_aliases)
nbconvert_aliases.update({
    'to' : 'NbConvertApp.export_format',
    'template' : 'TemplateExporter.template_file',
    'writer' : 'NbConvertApp.writer_class',
    'post': 'NbConvertApp.postprocessor_class',
    'output': 'NbConvertApp.output_base',
    'output-dir': 'FilesWriter.build_directory',
    'reveal-prefix': 'SlidesExporter.reveal_url_prefix',
    'nbformat': 'NotebookExporter.nbformat_version',
})

nbconvert_flags = {}
nbconvert_flags.update(base_flags)
nbconvert_flags.update({
    'execute' : (
        {'ExecutePreprocessor' : {'enabled' : True}},
        "Execute the notebook prior to export."
        ),
    'allow-errors' : (
        {'ExecutePreprocessor' : {'allow_errors' : True}},
        ("Continue notebook execution even if one of the cells throws "
         "an error and include the error message in the cell output "
         "(the default behaviour is to abort conversion). This flag "
         "is only relevant if '--execute' was specified, too.")
        ),
    'stdin' : (
        {'NbConvertApp' : {
            'from_stdin' : True,
            }
        },
        "read a single notebook file from stdin. Write the resulting notebook with default basename 'notebook.*'"
        ),
    'stdout' : (
        {'NbConvertApp' : {'writer_class' : "StdoutWriter"}},
        "Write notebook output to stdout instead of files."
        ),
    'inplace' : (
        {
            'NbConvertApp' : {
                'use_output_suffix' : False,
                'export_format' : 'notebook',
            },
            'FilesWriter' : {'build_directory': ''},
        },
        """Run nbconvert in place, overwriting the existing notebook (only 
        relevant when converting to notebook format)"""
        ),
    'clear-output' : (
        {
            'NbConvertApp' : {
                'use_output_suffix' : False,
                'export_format' : 'notebook',
            },
            'FilesWriter' : {'build_directory': ''},
            'ClearOutputPreprocessor' : {'enabled' : True},
        },
        """Clear output of current file and save in place, 
        overwriting the existing notebook. """
        ),
    'no-prompt' : (
        {'TemplateExporter' : {
            'exclude_input_prompt' : True,
            'exclude_output_prompt' : True,
            }
        },
        "Exclude input and output prompts from converted document."
        ),
})


class NbConvertApp(JupyterApp):
    """Application used to convert from notebook file type (``*.ipynb``)"""
    
    version = __version__
    name = 'jupyter-nbconvert'
    aliases = nbconvert_aliases
    flags = nbconvert_flags
    
    @default('log_level')
    def _log_level_default(self):
        return logging.INFO
    
    classes = List()
    @default('classes')
    def _classes_default(self):
        classes = [NbConvertBase]
        for pkg in (exporters, preprocessors, writers, postprocessors):
            for name in dir(pkg):
                cls = getattr(pkg, name)
                if isinstance(cls, type) and issubclass(cls, Configurable):
                    classes.append(cls)
        
        return classes

    description = Unicode(
        u"""This application is used to convert notebook files (*.ipynb)
        to various other formats.

        WARNING: THE COMMANDLINE INTERFACE MAY CHANGE IN FUTURE RELEASES.""")

    output_base = Unicode('', help='''overwrite base name use for output files.
            can only be used when converting one notebook at a time.
            ''').tag(config=True)

    use_output_suffix = Bool(
        True, 
        help="""Whether to apply a suffix prior to the extension (only relevant
            when converting to notebook format). The suffix is determined by
            the exporter, and is usually '.nbconvert'."""
    ).tag(config=True)

    output_files_dir = Unicode('{notebook_name}_files',
         help='''Directory to copy extra files (figures) to.
               '{notebook_name}' in the string will be converted to notebook
               basename'''
    ).tag(config=True)

    examples = Unicode(u"""
        The simplest way to use nbconvert is
        
        > jupyter nbconvert mynotebook.ipynb
        
        which will convert mynotebook.ipynb to the default format (probably HTML).
        
        You can specify the export format with `--to`.
        Options include {0}
        
        > jupyter nbconvert --to latex mynotebook.ipynb

        Both HTML and LaTeX support multiple output templates. LaTeX includes
        'base', 'article' and 'report'.  HTML includes 'basic' and 'full'. You
        can specify the flavor of the format used.

        > jupyter nbconvert --to html --template basic mynotebook.ipynb
        
        You can also pipe the output to stdout, rather than a file
        
        > jupyter nbconvert mynotebook.ipynb --stdout

        PDF is generated via latex

        > jupyter nbconvert mynotebook.ipynb --to pdf
        
        You can get (and serve) a Reveal.js-powered slideshow
        
        > jupyter nbconvert myslides.ipynb --to slides --post serve
        
        Multiple notebooks can be given at the command line in a couple of 
        different ways:
  
        > jupyter nbconvert notebook*.ipynb
        > jupyter nbconvert notebook1.ipynb notebook2.ipynb
        
        or you can specify the notebooks list in a config file, containing::
        
            c.NbConvertApp.notebooks = ["my_notebook.ipynb"]
        
        > jupyter nbconvert --config mycfg.py
        """.format(get_export_names()))

    # Writer specific variables
    writer = Instance('nbconvert.writers.base.WriterBase',
                      help="""Instance of the writer class used to write the 
                      results of the conversion.""", allow_none=True)
    writer_class = DottedObjectName('FilesWriter',
                                    help="""Writer class used to write the 
                                    results of the conversion""").tag(config=True)
    writer_aliases = {'fileswriter': 'nbconvert.writers.files.FilesWriter',
                      'debugwriter': 'nbconvert.writers.debug.DebugWriter',
                      'stdoutwriter': 'nbconvert.writers.stdout.StdoutWriter'}
    writer_factory = Type(allow_none=True)
    
    @observe('writer_class')
    def _writer_class_changed(self, change):
        new = change['new']
        if new.lower() in self.writer_aliases:
            new = self.writer_aliases[new.lower()]
        self.writer_factory = import_item(new)

    # Post-processor specific variables
    postprocessor = Instance('nbconvert.postprocessors.base.PostProcessorBase',
                      help="""Instance of the PostProcessor class used to write the
                      results of the conversion.""", allow_none=True)

    postprocessor_class = DottedOrNone(
                                    help="""PostProcessor class used to write the
                                    results of the conversion"""
    ).tag(config=True)
    postprocessor_aliases = {'serve': 'nbconvert.postprocessors.serve.ServePostProcessor'}
    postprocessor_factory = Type(None, allow_none=True)
    
    @observe('postprocessor_class')
    def _postprocessor_class_changed(self, change):
        new = change['new']
        if new.lower() in self.postprocessor_aliases:
            new = self.postprocessor_aliases[new.lower()]
        if new:
            self.postprocessor_factory = import_item(new)


    export_format = Unicode(
        'html',
        allow_none=False,
        help="""The export format to be used, either one of the built-in formats,
        or a dotted object name that represents the import path for an
        `Exporter` class"""
    ).tag(config=True)

    notebooks = List([], help="""List of notebooks to convert.
                     Wildcards are supported.
                     Filenames passed positionally will be added to the list.
                     """
    ).tag(config=True)
    from_stdin = Bool(False, help="read a single notebook from stdin.").tag(config=True)

    @catch_config_error
    def initialize(self, argv=None):
        """Initialize application, notebooks, writer, and postprocessor"""
        self.init_syspath()
        super(NbConvertApp, self).initialize(argv)
        self.init_notebooks()
        self.init_writer()
        self.init_postprocessor()

    def init_syspath(self):
        """Add the cwd to the sys.path ($PYTHONPATH)"""
        sys.path.insert(0, os.getcwd())

    def init_notebooks(self):
        """Construct the list of notebooks.

        If notebooks are passed on the command-line,
        they override (rather than add) notebooks specified in config files.
        Glob each notebook to replace notebook patterns with filenames.
        """

        # Specifying notebooks on the command-line overrides (rather than
        # adds) the notebook list
        if self.extra_args:
            patterns = self.extra_args
        else:
            patterns = self.notebooks

        # Use glob to replace all the notebook patterns with filenames.
        filenames = []
        for pattern in patterns:
            
            # Use glob to find matching filenames.  Allow the user to convert 
            # notebooks without having to type the extension.
            globbed_files = glob.glob(pattern)
            globbed_files.extend(glob.glob(pattern + '.ipynb'))
            if not globbed_files:
                self.log.warn("pattern %r matched no files", pattern)

            for filename in globbed_files:
                if not filename in filenames:
                    filenames.append(filename)
        self.notebooks = filenames

    def init_writer(self):
        """Initialize the writer (which is stateless)"""
        self._writer_class_changed({ 'new': self.writer_class })
        self.writer = self.writer_factory(parent=self)
        if hasattr(self.writer, 'build_directory') and self.writer.build_directory != '':
            self.use_output_suffix = False

    def init_postprocessor(self):
        """Initialize the postprocessor (which is stateless)"""
        self._postprocessor_class_changed({'new': self.postprocessor_class})
        if self.postprocessor_factory:
            self.postprocessor = self.postprocessor_factory(parent=self)

    def start(self):
        """Run start after initialization process has completed"""
        super(NbConvertApp, self).start()
        self.convert_notebooks()

    def init_single_notebook_resources(self, notebook_filename):
        """Step 1: Initialize resources

        This initializes the resources dictionary for a single notebook.

        Returns
        -------

        dict
            resources dictionary for a single notebook that MUST include the following keys:
                - config_dir: the location of the Jupyter config directory
                - unique_key: the notebook name
                - output_files_dir: a directory where output files (not
                  including the notebook itself) should be saved
        """
        basename = os.path.basename(notebook_filename)
        notebook_name = basename[:basename.rfind('.')]
        if self.output_base:
            # strip duplicate extension from output_base, to avoid Basename.ext.ext
            if getattr(self.exporter, 'file_extension', False):
                base, ext = os.path.splitext(self.output_base)
                if ext == self.exporter.file_extension:
                    self.output_base = base
            notebook_name = self.output_base

        self.log.debug("Notebook name is '%s'", notebook_name)

        # first initialize the resources we want to use
        resources = {}
        resources['config_dir'] = self.config_dir
        resources['unique_key'] = notebook_name

        output_files_dir = (self.output_files_dir
                            .format(notebook_name=notebook_name))

        resources['output_files_dir'] = output_files_dir

        return resources

    def export_single_notebook(self, notebook_filename, resources, input_buffer=None):
        """Step 2: Export the notebook

        Exports the notebook to a particular format according to the specified
        exporter. This function returns the output and (possibly modified)
        resources from the exporter.

        Parameters
        ----------
        notebook_filename : str
            name of notebook file.
        resources : dict
        input_buffer :
            readable file-like object returning unicode.
            if not None, notebook_filename is ignored

        Returns
        -------
        output

        dict
            resources (possibly modified)
        """
        try:
            if input_buffer is not None:
                output, resources = self.exporter.from_file(input_buffer, resources=resources)
            else:
                output, resources = self.exporter.from_filename(notebook_filename, resources=resources)
        except ConversionException:
            self.log.error("Error while converting '%s'", notebook_filename, exc_info=True)
            self.exit(1)

        return output, resources

    def write_single_notebook(self, output, resources):
        """Step 3: Write the notebook to file

        This writes output from the exporter to file using the specified writer.
        It returns the results from the writer.

        Parameters
        ----------
        output :
        resources : dict
            resources for a single notebook including name, config directory
            and directory to save output

        Returns
        -------
        file
            results from the specified writer output of exporter
        """
        if 'unique_key' not in resources:
            raise KeyError("unique_key MUST be specified in the resources, but it is not")

        notebook_name = resources['unique_key']
        if self.use_output_suffix and not self.output_base:
            notebook_name += resources.get('output_suffix', '')

        write_results = self.writer.write(
            output, resources, notebook_name=notebook_name)
        return write_results

    def postprocess_single_notebook(self, write_results):
        """Step 4: Post-process the written file

        Only used if a postprocessor has been specified. After the
        converted notebook is written to a file in Step 3, this post-processes
        the notebook.
        """
        # Post-process if post processor has been defined.
        if hasattr(self, 'postprocessor') and self.postprocessor:
            self.postprocessor(write_results)

    def convert_single_notebook(self, notebook_filename, input_buffer=None):
        """Convert a single notebook.

        Performs the following steps:

            1. Initialize notebook resources
            2. Export the notebook to a particular format
            3. Write the exported notebook to file
            4. (Maybe) postprocess the written file

        Parameters
        ----------
        notebook_filename : str
        input_buffer :
            If input_buffer is not None, conversion is done and the buffer is
            used as source into a file basenamed by the notebook_filename
            argument.
        """
        if input_buffer is None:
            self.log.info("Converting notebook %s to %s", notebook_filename, self.export_format)
        else:
            self.log.info("Converting notebook into %s", self.export_format)
        
        resources = self.init_single_notebook_resources(notebook_filename)
        output, resources = self.export_single_notebook(notebook_filename, resources, input_buffer=input_buffer)
        write_results = self.write_single_notebook(output, resources)
        self.postprocess_single_notebook(write_results)

    def convert_notebooks(self):
        """Convert the notebooks in the self.notebook traitlet """
        # check that the output base isn't specified if there is more than
        # one notebook to convert
        if self.output_base != '' and len(self.notebooks) > 1:
            self.log.error(
                """
                UsageError: --output flag or `NbConvertApp.output_base` config option
                cannot be used when converting multiple notebooks.
                """
            )
            self.exit(1)
        
        # initialize the exporter
        cls = get_exporter(self.export_format)
        self.exporter = cls(config=self.config)

        # no notebooks to convert!
        if len(self.notebooks) == 0 and not self.from_stdin:
            self.print_help()
            sys.exit(-1)

        # convert each notebook
        if not self.from_stdin:
            for notebook_filename in self.notebooks:
                self.convert_single_notebook(notebook_filename)
        else:
            input_buffer = unicode_stdin_stream()
            # default name when conversion from stdin
            self.convert_single_notebook("notebook.ipynb", input_buffer=input_buffer)
            
#-----------------------------------------------------------------------------
# Main entry point
#-----------------------------------------------------------------------------

main = launch_new_instance = NbConvertApp.launch_instance