def test_authors(self):
self.assert_parse(
"Carroll, Lewis, 1832-1898",
"Carroll, Lewis", Contributor.PRIMARY_AUTHOR_ROLE, "1832", "1898")
self.assert_parse(
"Kent, Rockwell, 1882-1971 [Illustrator]",
"Kent, Rockwell", "Illustrator",
"1882", "1971")
self.assert_parse(
u"Карролл, Лувис, 1832-1898.",
u"Карролл, Лувис", Contributor.PRIMARY_AUTHOR_ROLE,
birthdate="1832", deathdate="1898")
kerry, melville = OCLCXMLParser.parse_author_string(
self._db,
"McSweeney, Kerry, 1941- | Melville, Herman, 1819-1891")
self.assert_author(kerry, "McSweeney, Kerry",
Contributor.PRIMARY_AUTHOR_ROLE,
birthdate="1941", deathdate=self.MISSING)
self.assert_author(
melville, "Melville, Herman", Contributor.AUTHOR_ROLE,
birthdate="1819", deathdate="1891")
# Check out this mess.
s = "Sunzi, active 6th century B.C. | Giles, Lionel, 1875-1958 [Writer of added commentary; Translator] | Griffith, Samuel B. [Editor; Author of introduction; Translator] | Cleary, Thomas F., 1949- [Editor; Translator] | Sawyer, Ralph D. [Editor; Author of introduction; Translator] | Clavell, James"
sunzi, giles, griffith, cleary, sawyer, clavell = (
OCLCXMLParser.parse_author_string(self._db, s))
# This one could be better.
self.assert_author(sunzi, "Sunzi, active 6th century B.C.",
Contributor.PRIMARY_AUTHOR_ROLE)
self.assert_author(giles, "Giles, Lionel",
["Writer of added commentary", "Translator"],
"1875", "1958")
self.assert_author(griffith, "Griffith, Samuel B.",
["Editor", "Author of introduction", "Translator"],
self.MISSING, self.MISSING)
self.assert_author(
cleary, "Cleary, Thomas F.", ["Editor", "Translator"],
"1949", self.MISSING)
self.assert_author(
sawyer, "Sawyer, Ralph D.", ["Editor", "Author of introduction",
"Translator"],
self.MISSING, self.MISSING)
# Once contributors start getting explicit roles, a
# contributor with no explicit role is treated as 'unknown'
# rather than 'author.'
self.assert_author(
clavell, "Clavell, James", [Contributor.UNKNOWN_ROLE],
self.MISSING, self.MISSING)
# These are titles we don't parse as well as we ought, but
# we are able to handle them without crashing.
self.assert_parse(
u"梅爾維爾 (Melville, Herman), 1819-1891",
u"梅爾維爾 (Melville, Herman)", Contributor.PRIMARY_AUTHOR_ROLE,
birthdate="1819", deathdate="1891")
self.assert_parse(
u"卡洛爾 (Carroll, Lewis), (英), 1832-1898",
u"卡洛爾 (Carroll, Lewis), (英)", Contributor.PRIMARY_AUTHOR_ROLE,
birthdate="1832", deathdate="1898")
s = u"杜格孫 (Dodgson, Charles Lutwidge,1832-1896)"
self.assert_parse(s, s, Contributor.PRIMARY_AUTHOR_ROLE)
def test_authors(self):
self.assert_parse(
"Carroll, Lewis, 1832-1898", "Carroll, Lewis", Contributor.PRIMARY_AUTHOR_ROLE, "1832", "1898"
)
self.assert_parse("Kent, Rockwell, 1882-1971 [Illustrator]", "Kent, Rockwell", "Illustrator", "1882", "1971")
self.assert_parse(
u"Карролл, Лувис, 1832-1898.",
u"Карролл, Лувис",
Contributor.PRIMARY_AUTHOR_ROLE,
birthdate="1832",
deathdate="1898",
)
kerry, melville = OCLCXMLParser.parse_author_string(
self._db, "McSweeney, Kerry, 1941- | Melville, Herman, 1819-1891"
)
self.assert_author(
kerry, "McSweeney, Kerry", Contributor.PRIMARY_AUTHOR_ROLE, birthdate="1941", deathdate=self.MISSING
)
self.assert_author(melville, "Melville, Herman", Contributor.AUTHOR_ROLE, birthdate="1819", deathdate="1891")
# Check out this mess.
s = "Sunzi, active 6th century B.C. | Giles, Lionel, 1875-1958 [Writer of added commentary; Translator] | Griffith, Samuel B. [Editor; Author of introduction; Translator] | Cleary, Thomas F., 1949- [Editor; Translator] | Sawyer, Ralph D. [Editor; Author of introduction; Translator] | Clavell, James"
sunzi, giles, griffith, cleary, sawyer, clavell = OCLCXMLParser.parse_author_string(self._db, s)
# This one could be better.
self.assert_author(sunzi, "Sunzi, active 6th century B.C.", Contributor.PRIMARY_AUTHOR_ROLE)
self.assert_author(giles, "Giles, Lionel", ["Writer of added commentary", "Translator"], "1875", "1958")
self.assert_author(
griffith,
"Griffith, Samuel B.",
["Editor", "Author of introduction", "Translator"],
self.MISSING,
self.MISSING,
)
self.assert_author(cleary, "Cleary, Thomas F.", ["Editor", "Translator"], "1949", self.MISSING)
self.assert_author(
sawyer, "Sawyer, Ralph D.", ["Editor", "Author of introduction", "Translator"], self.MISSING, self.MISSING
)
# Once contributors start getting explicit roles, a
# contributor with no explicit role is treated as 'unknown'
# rather than 'author.'
self.assert_author(clavell, "Clavell, James", [Contributor.UNKNOWN_ROLE], self.MISSING, self.MISSING)
# These are titles we don't parse as well as we ought, but
# we are able to handle them without crashing.
self.assert_parse(
u"梅爾維爾 (Melville, Herman), 1819-1891",
u"梅爾維爾 (Melville, Herman)",
Contributor.PRIMARY_AUTHOR_ROLE,
birthdate="1819",
deathdate="1891",
)
self.assert_parse(
u"卡洛爾 (Carroll, Lewis), (英), 1832-1898",
u"卡洛爾 (Carroll, Lewis), (英)",
Contributor.PRIMARY_AUTHOR_ROLE,
birthdate="1832",
deathdate="1898",
)
s = u"杜格孫 (Dodgson, Charles Lutwidge,1832-1896)"
self.assert_parse(s, s, Contributor.PRIMARY_AUTHOR_ROLE)
def assert_parse(self, string, name, role=Contributor.AUTHOR_ROLE,
birthdate=None, deathdate=None):
[res] = OCLCXMLParser.parse_author_string(self._db, string)
self.assert_author(res, name, role, birthdate, deathdate)
def assert_parse(self, string, name, role=Contributor.AUTHOR_ROLE, birthdate=None, deathdate=None):
[res] = OCLCXMLParser.parse_author_string(self._db, string)
self.assert_author(res, name, role, birthdate, deathdate)