import requests
import pandas as pd
import matplotlib.pyplot as plt

# 1. Extraction: Connect to public JSON endpoints dynamically
url = "https://raw.githubusercontent.com/jokecamp/FootballData/master/FIFA-World-Cups/2026/2026-fixtures.json"
response = requests.get(url)
raw_data = response.json()

# 2. Ingestion & Flattening: Reconstruct multi-tiered nested tables
matches_df = pd.json_normalize(raw_data['matches'])

# 3. Engineering: Normalizing timestamps and categorizing operational metrics
matches_df['parsed_date'] = pd.to_datetime(matches_df['date'])
matches_df['match_week'] = matches_df['parsed_date'].dt.isocalendar().week

# 4. Analysis Validation Output Pipeline
print(f"Ingested {len(matches_df)} operational records successfully.")

# 5. Visualizing structural performance trends
plt.figure(figsize=(10, 5))
matches_df['venue'].value_counts().plot(kind='bar', color='#4c7dff')
plt.title('Match Density Vectors across Venues')
plt.ylabel('Total Matches Hosted')
plt.tight_layout()
# View simulated output graphs locally

SELECT
    T0.[TransId]       AS [Transaction Number],
    T4.[DocEntry]      AS [Internal Number],
    T0.[RefDate]       AS [Posting Date],
    CASE
        WHEN T4.[CANCELED] = 'Y' THEN 'Canceled'
        WHEN T4.[DocStatus] = 'C' THEN 'Closed'
        WHEN T4.[DocStatus] = 'O' THEN 'Open'
        ELSE 'Other'
    END                AS [DocStatus],
    CASE T1.[TransType]
        WHEN 18 THEN 'A/P Invoice'
        WHEN 30 THEN 'Journal Entry'
        WHEN 46 THEN 'Outgoing Payment'
        ELSE ''
    END                AS [DocTypeName],
    T1.[Account]       AS [Account Code],
    T2.[AcctName]      AS [Account Name],
    T4.[U_PANNo]       AS [PAN No.],
    Exp.[AcctName]     AS [Expense Name],
    T1.[Project]       AS [Project Code],
    T1.[OcrCode2]      AS [Costing Code 2],
    DR2.[OcrName]      AS [TDS Party Name],
    CASE
        WHEN CA.NetTDS > 0 THEN ROUND(T1.[U_TDSGrossAmt], 4)
        ELSE -ROUND(T1.[U_TDSGrossAmt], 4)
    END                AS [F_GrossValue],
    T1.[Debit]         AS [Debit TDS Amt],
    T1.[Credit]        AS [Credit TDS Amt],
    (ISNULL(T1.[U_TDSGrossAmt], 0) - ISNULL(T1.[Credit], 0)) AS [Payable Amt],
    T1.[LineMemo]      AS [Row Details],
    T5.[U_NAME]        AS [User Name],
    ROUND(T1.[U_TDSGrossAmt], 4) AS TDSGrossValue,
    CA.NetTDS,
    CA.TDSPer,
    CONVERT(varchar(16), CAST(ROUND(CA.TDSPer * 100.0, 2) AS DECIMAL(10,2))) + ' %' AS TDSPct,
    HX.Helper,
    SUM(CA.NetTDS) OVER (
        PARTITION BY HX.Helper
        ORDER BY T0.[RefDate], T0.[TransId], T1.[Line_ID]
        ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW
    ) AS CumulativeNetTDS,
    DR2.[U_PANNO] AS TDSPANNo,
    BP.[CardName] AS BPName,
    BP.[U_PANNo]  AS BPPAN,
    CASE
        WHEN DR2.[U_PANNO] IS NOT NULL
         AND UPPER(LTRIM(RTRIM(BP.[U_PANNo]))) = UPPER(LTRIM(RTRIM(DR2.[U_PANNO])))
        THEN 'Y' ELSE 'N'
    END AS PANMatch,
    CASE WHEN T1.[TransType] = 18 THEN EG.EntryGrossValue ELSE NULL END AS EntryGrossValue,
    CASE
        WHEN T1.[TransType] = 18 AND ROUND(T1.[U_TDSGrossAmt], 4) = EG.EntryGrossValue THEN 'Y'
        WHEN T1.[TransType] = 18 THEN 'N'
        ELSE NULL
    END AS GVCheck
FROM OJDT T0
JOIN JDT1 T1           ON T0.[TransId] = T1.[TransId]
JOIN OACT T2           ON T1.[Account]  = T2.[AcctCode]
LEFT JOIN OPCH T4      ON T4.[TransId]  = T0.[TransId]
JOIN OUSR T5           ON T0.[UserSign] = T5.[USERID]
LEFT JOIN OOCR DR2     ON DR2.[OcrCode] = T1.[OcrCode2] AND DR2.[DimCode] = 2
LEFT JOIN OCRD BP      ON BP.[CardCode] = T4.[CardCode] AND BP.[CardType] = 'S'
OUTER APPLY (
    SELECT TOP (1) O2.[AcctName]
    FROM JDT1 J
    JOIN OACT O2 ON O2.[AcctCode] = J.[Account]
    WHERE J.[TransId] = T1.[TransId]
    AND (
        O2.[AcctCode] LIKE '53%' OR O2.[AcctCode] LIKE '52%' OR 
        O2.[AcctCode] LIKE '117%' OR O2.[AcctCode] LIKE '224%' OR 
        O2.[AcctCode] LIKE '11%' OR O2.[AcctCode] LIKE '12%'
    )
    ORDER BY
        CASE
            WHEN O2.[AcctCode] LIKE '53%' OR O2.[AcctCode] LIKE '52%' THEN 0
            WHEN O2.[AcctCode] LIKE '117%' THEN 1
            WHEN O2.[AcctCode] LIKE '224%' THEN 2
            WHEN O2.[AcctCode] LIKE '11%' THEN 3
            WHEN O2.[AcctCode] LIKE '12%' THEN 4 
            ELSE 5
        END,
        O2.[AcctCode]
) AS Exp
CROSS APPLY (
    SELECT
        NetTDS = ISNULL(T1.[Credit], 0) - ISNULL(T1.[Debit], 0),
        TDSPer = CASE
            WHEN NULLIF(T1.[U_TDSGrossAmt], 0) IS NULL THEN NULL
            ELSE (ISNULL(T1.[Credit], 0) - ISNULL(T1.[Debit], 0)) / NULLIF(T1.[U_TDSGrossAmt], 0)
        END
) AS CA
CROSS APPLY (
    SELECT Helper = CONCAT(
        T2.[AcctName], '-', ISNULL(T1.[OcrCode2], ''), '-',
        CONVERT(varchar(32), CAST(CA.TDSPer AS DECIMAL(18,6)))
    )
) AS HX
OUTER APPLY (
    SELECT
        CASE WHEN T1.[Credit] <> 0 THEN SUM(J.[Debit]) ELSE SUM(J.[Credit]) END AS EntryGrossValue
    FROM JDT1 J
    JOIN OACT OA ON OA.[AcctCode] = J.[Account]
    WHERE J.[TransId] = T1.[TransId]
    AND UPPER(LTRIM(RTRIM(OA.[AcctName]))) NOT IN ('VALUE ADDED TAX', 'VAT PROVISION A/C')
) AS EG
WHERE
    T0.[RefDate] >= [%0]
    AND T0.[RefDate] <= [%1]
    AND (
        (NULLIF('[%2]', '') IS NULL AND T1.[Account] IN ('2232500','2232400','2232300','2230027','2230025','2235000','2234000','2232904','2230031'))
        OR (NULLIF('[%2]', '') IS NOT NULL AND T2.[AcctName] = '[%2]')
    )
ORDER BY
    T2.[AcctName] ASC,
    T1.[OcrCode2] ASC,
    CA.TDSPer ASC,
    T0.[RefDate] ASC,
    T0.[TransId] ASC,
    T1.[Line_ID] ASC;