PYield 0.2.11__tar.gz → 0.2.13__tar.gz

{pyield-0.2.11 → pyield-0.2.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: PYield
-Version: 0.2.11
+Version: 0.2.13
 Summary: A Python library for analysis of fixed income instruments in Brazil
 Keywords: fixed-income, brazil, finance, analysis, bonds
 Author-Email: Carlos Carvalho <cr.cj@outlook.com>

pyield-0.2.13/pyield/__about__.py

@@ -0,0 +1 @@
+__version__ = "0.2.13"

{pyield-0.2.11 → pyield-0.2.13}/pyield/di_html.py

@@ -188,7 +188,11 @@ def process_di(df: pd.DataFrame, reference_date: pd.Timestamp) -> pd.DataFrame:
             "ÚLT.OF. VENDA": "last_offer_rate",
         }
     )
-    reference_date = pd.Timestamp(reference_date)
+
+    df.insert(0, "reference_date", reference_date)
+    # Convert to datetime64[ns] since it is pandas default type for timestamps
+    df["reference_date"] = df["reference_date"].astype("datetime64[ns]")
+
     # Contract code format was changed in 22/05/2006
     if reference_date < pd.Timestamp("2006-05-22"):
         df["expiration"] = df["contract_code"].apply(
@@ -232,6 +236,7 @@ def process_di(df: pd.DataFrame, reference_date: pd.Timestamp) -> pd.DataFrame:
     # Order columns
     df = df[
         [
+            "reference_date",
             "contract_code",
             "expiration",
             "bdays",

{pyield-0.2.11 → pyield-0.2.13}/pyield/di_xml.py

@@ -34,14 +34,19 @@ def extract_xml_file(zip_file: io.BytesIO) -> io.BytesIO:
 
     # Then, read the inner file
     with zipfile.ZipFile(outer_file, "r") as inner_zip:
-        inner_file_name = inner_zip.namelist()[0]
-        inner_file_content = inner_zip.read(inner_file_name)
+        filenames = inner_zip.namelist()
+        # Get first file that ends with ".xml"
+        xml_filename = [name for name in filenames if name.endswith(".xml")][0]
+        inner_file_content = inner_zip.read(xml_filename)
 
     return io.BytesIO(inner_file_content)
 
 
 def parse_xml_file(xml_file: io.BytesIO) -> list:
-    tree = etree.parse(xml_file)
+    parser = etree.XMLParser(
+        ns_clean=True, remove_blank_text=True, remove_comments=True, recover=True
+    )
+    tree = etree.parse(xml_file, parser)
     # Definir os namespaces (substitua 'ns' pelo prefixo apropriado se necessário)
     namespaces = {"ns": "urn:bvmf.217.01.xsd"}
 
@@ -92,13 +97,17 @@ def process_df(df_raw: pd.DataFrame, reference_date: pd.Timestamp) -> pd.DataFra
     # Remover colunas cujos dados são constantes: MktDataStrmId, AdjstdQtStin e PrvsAdjstdQtStin
     df.drop(columns=["MktDataStrmId", "AdjstdQtStin", "PrvsAdjstdQtStin"], inplace=True)
 
+    df.insert(0, "RptDt", reference_date)
+    # Convert to datetime64[ns] since it is pandas default type for timestamps
+    df["RptDt"] = df["RptDt"].astype("datetime64[ns]")
+
     expiration = df["TckrSymb"].str[3:].apply(dif.get_expiration_date)
     # Insert the column at the beginning
-    df.insert(1, "ExpDt", expiration)
+    df.insert(2, "ExpDt", expiration)
 
     business_days = brc.count_bdays(reference_date, df["ExpDt"])
     # Insert the column at the beginning
-    df.insert(2, "BDaysToExp", business_days)
+    df.insert(3, "BDaysToExp", business_days)
     # Convert to nullable integer, since other columns use this data type
     df["BDaysToExp"] = df["BDaysToExp"].astype(pd.Int64Dtype())
     # Remove expired contracts

{pyield-0.2.11 → pyield-0.2.13}/pyproject.toml

@@ -31,7 +31,7 @@ dependencies = [
     "lxml",
 ]
 dynamic = []
-version = "0.2.11"
+version = "0.2.13"
 
 [project.license]
 file = "LICENSE"

pyield-0.2.11/pyield/__about__.py

@@ -1 +0,0 @@
-__version__ = "0.2.11"