# Inputs: document_string (a str)

import spacy

# Load a language model and parse a document.
nlp = spacy.load('en')
doc = nlp(document_string)

# Find named entities.
for ent in doc.ents:
    print(ent)  # Each `ent` is a `Span` object.

# Recover entity substrings in the source document.
for ent in doc.ents:
    substring = document_string[ent.start_char: ent.end_char]

import spacy


# Set up functions to help produce human-friendly printing.
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

def skip_and_print(*args):
    """ Act like print(), but skip a line before printing. """
    print('\n' + str(args[0]), *args[1:])

def print_table(rows):
    """ Print `rows` with content-based column widths. """
    col_widths = [
        max(len(str(value)) for value in col)
        for col in zip(*rows)
    ]
    total_width = sum(col_widths) + len(col_widths) - 1
    fmt = ' '.join('%%-%ds' % width for width in col_widths)
    print(fmt % tuple(rows[0]))
    print('~' * total_width)
    for row in rows[1:]:
        print(fmt % tuple(row))


# Load a language model and parse a document.
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

nlp = spacy.load('en')

document_string = "I like to visit Park Tea House in Berkeley."

skip_and_print('Working with string: "%s"' % document_string)
doc = nlp(document_string)


# Finding named entities.
# ~~~~~~~~~~~~~~~~~~~~~~~

rows = [['Name', 'Start', 'End', 'Label']]

# Each `ent` object is an instance of the `Span` class.
for ent in doc.ents:
    rows.append([
        ent.text,        # The str of the named entity phrase.
        ent.start_char,  # Source str index of the first char.
        ent.end_char,    # Source str index of the last+1 char.
        ent.label_       # A str label for the entity type.
    ])

skip_and_print('Named entities found:')
print_table(rows)

# Named entities found:
#
# Name           Start End Label
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# Park Tea House 16    30  ORG
# Berkeley       34    42  GPE

# Example entity types (values found in .label_):
#
#     ORG    = organization
#     GPE    = geo-political entity
#     PERSON = person (may be fictional!)


# Recovering substrings of named entities in your source.
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

# This an example of recovering the original substring from your
# document. This can be useful, for example, if you're working
# with a pipeline that thinks in terms of character indexes in a
# master document.

for ent in doc.ents:
    skip_and_print('Recovering "%s":' % ent)
    print(document_string)
    print(' ' * ent.start_char + '^' * len(ent.text))

    # How you can access the entity subtring using a slice:
    substr = document_string[ent.start_char: ent.end_char]

# Recovering "Park Tea House":
# I like to visit Park Tea House in Berkeley.
#                 ^^^^^^^^^^^^^^
#
# Recovering "Berkeley":
# I like to visit Park Tea House in Berkeley.
#                                   ^^^^^^^^