def write_metadata(context, metadata: dp.DataFrame, to_tag):
"""
Write available metadata, including GPS tags,
to high-res JPEGs
"""
metadata.fillna(value="", inplace=True)
metadata["Source ID"] = metadata["Source ID"].str.upper()
metadata.set_index("Source ID", inplace=True)
for item in tqdm(to_tag, "Embedding metadata in files..."):
if item.endswith(".jpg"):
basename = os.path.split(item)[1]
name = basename.split(".")[0]
date = metadata.loc[name.upper(), "Date"]
byline = metadata.loc[name.upper(), "Creator"]
headline = metadata.loc[name.upper(), "Title"]
caption = metadata.loc[name.upper(), "Description (Portuguese)"]
objecttype = metadata.loc[name.upper(), "Type"]
# dimensions = f'{metadata.loc[name.upper(), "image_width"]}cm x {metadata.loc[name.upper(), "image_height"]}cm'
keywords = metadata.loc[name.upper(), "Depicts"].split("||")
latitude = metadata.loc[name.upper(), "Latitude"]
longitude = metadata.loc[name.upper(), "Longitude"]
# altitude = metadata.loc[name.upper(), "Altitude"]
# imgdirection = metadata.loc[name.upper(), "heading"]
params = [
"-IPTC:Source=Instituto Moreira Salles/IMS",
"-IPTC:CopyrightNotice=This image is in the Public Domain.",
"-IPTC:City=Rio de Janeiro",
"-IPTC:Province-State=RJ",
"-IPTC:Country-PrimaryLocationName=Brasil",
"-GPSLatitudeRef=S",
"-GPSLongitudeRef=W",
"-GPSAltitudeRef=0",
"-GPSImgDirectionRef=T",
f"-IPTC:DateCreated={date}",
f"-IPTC:By-line={byline}",
f"-IPTC:ObjectName={name}",
f"-IPTC:Headline={headline}",
f"-IPTC:Caption-Abstract={caption}",
f"-IPTC:ObjectTypeReference={objecttype}",
# f"-IPTC:Dimensions={dimensions}",
f"-IPTC:Keywords={keywords}",
f"-GPSLatitude={latitude}",
f"-GPSLongitude={longitude}",
# f"-GPSAltitude={altitude}",
# f"-GPSImgDirection={imgdirection}",
]
with ExifTool(executable_=context.solid_config) as et:
for param in params:
param = param.encode(encoding="utf-8")
dest = item.encode(encoding="utf-8")
et.execute(param, dest)
to_upload = to_tag
return to_upload
def transform_table_desc_df(context, table_desc: DataFrame) -> DataFrame:
"""
Transform the DataFrame of data types in database table
:param context: execution context
:param table_desc: panda DataFrame containing details of the Postgres database table
:return: panda DataFrame containing details of the Postgres database table
:rtype: panda.DataFrame
"""
table_desc.fillna('', inplace=True)
# get names of indices for which column ignore contains #. i.e. comment lines
index_names = table_desc[table_desc['ignore'].str.contains('#')].index
# drop comment row indexes from dataFrame
table_desc.drop(index_names, inplace=True)
# drop column ignore from dataFrame
table_desc.drop(['ignore'], axis=1, inplace=True)
return table_desc
def organise_creator(_, quickstate: dp.DataFrame):
creators = {
"Augusto Malta": "Q16495239",
"Anônimo": "Q4233718",
"Marc Ferrez": "Q3180571",
"Georges Leuzinger": "Q5877879",
"José dos Santos Affonso": "Q63993961",
"N. Viggiani": "Q65619909",
"Archanjo Sobrinho": "Q64009665",
"F. Basto": "Q55089601",
"J. Faria de Azevedo": "Q97570600",
"S. H. Holland": "Q65619918",
"Augusto Monteiro": "Q65619921",
"Jorge Kfuri": "Q63166336",
"Camillo Vedani": "Q63109123",
"Fritz Büsch": "Q63109492",
"Armando Pittigliani": "Q19607834",
"Braz": "Q97487621",
"Stahl & Wahnschaffe": "Q63109157",
"Gomes Junior": "Q86942676",
"A. Ruelle": "Q97570551",
"Guilherme Santos": "Q55088608",
"Albert Frisch": "Q21288396",
"José Baptista Barreira Vianna": "Q63166517",
"Alfredo Krausz": "Q63166405",
"Therezio Mascarenhas": "Q97570728",
"Torres": "Q65619905",
"Theodor Preising": "Q63109140",
"Augusto Stahl": "Q4821327",
"Luiz Musso": "Q89538832",
"Carlos Bippus": "Q63109147",
"Thiele": "Q64825643",
"Revert Henrique Klumb": "Q3791061",
"Juan Gutierrez": "Q10312614",
"F. Manzière": "Q65619915",
"Antonio Luiz Ferreira": "Q97570558",
"Etienne Farnier": "Q97570575",
"José Francisco Corrêa": "Q10309433",
"Chapelin": "Q97570376",
"J. Teixeira": "Q89642578",
"F. Garcia": "Q97570588",
"A. de Barros Lobo": "Q97570363",
"Bloch": "Q61041099",
}
def name2qid(name):
"""
Takes a string and returns the
corresponding Wikidata QID
"""
try:
qid = creators[f"{name}"]
except KeyError:
qid = ""
return qid
quickstate["P170"] = quickstate["P170"].apply(name2qid)
quickstate = quickstate.drop(columns="date_accuracy")
quickstate.name = "import_wikidata"
def df2quickstatements(df):
create_str = ""
edit_str = ""
str_props = ["Lpt-br", "Dpt-br", "Den", "P217", "P7835"]
no_ref_props = ["Lpt-br", "Dpt-br", "Den"]
for _, row in df.iterrows():
row = dict(row)
props = []
if row["qid"]:
for key in row.keys():
if row[key]:
if key in str_props:
row[key] = '"{0}"'.format(row[key])
prop_str = "|".join([
str(row["qid"]),
str(key).replace("P31_a", "P31"),
str(row[key]),
])
if key == "P217":
prop_str += "|P195|Q71989864"
if key == "P195":
prop_str += "|P217|" + '"{0}"'.format(row["P217"])
if key not in no_ref_props:
prop_str += "|S248|Q64995339|S813|+{0}Z/11".format(
dt.now().strftime("%Y-%m-%dT00:00:00"))
props.append(prop_str)
item_str = "||".join(props)
if not edit_str:
edit_str += item_str
else:
edit_str += "||" + item_str
else:
props.append("CREATE")
for key in row.keys():
if row[key]:
if key in str_props:
row[key] = '"{0}"'.format(row[key])
prop_str = "|".join([
"LAST",
str(key).replace("P31_a", "P31"),
str(row[key]),
])
if key == "P217":
prop_str += "|P195|Q71989864"
if key == "P195":
prop_str += "|P217|" + '"{0}"'.format(row["P217"])
if key not in no_ref_props:
prop_str += "|S248|Q64995339|S813|+{0}Z/11".format(
dt.now().strftime("%Y-%m-%dT00:00:00"))
props.append(prop_str)
item_str = "||".join(props)
if not create_str:
create_str += item_str
else:
create_str += "||" + item_str
return {"create": create_str, "edit": edit_str}
quickstate.fillna("", inplace=True)
with open("data/output/quickstatements_create.txt", "w+") as f:
f.write(df2quickstatements(quickstate)["create"])
with open("data/output/quickstatements_edit.txt", "w+") as f:
f.write(df2quickstatements(quickstate)["edit"])
return quickstate.set_index("qid")