"交易日期","记账日期","卡末四位","交易说明","交易金额","入账金额"
"2011/01/16","2011/01/17","2987","消费 支付宝 - xxx科技有限公司","RMB 6.30","RMB 6.30"
"2011/01/18","2011/01/19","2987","消费 支付宝 - xxx科技有限公司","RMB 0.90","RMB 0.90"
"2011/01/19","2011/01/20","2987","消费 食堂","RMB 100.00","RMB 100.00"

export PYTHONPATH=.
bean-extract config.py datas/comm-2021.01.csv > beans/comm-2021.01.bean

"""CSV importer.
"""

import collections
import csv
import datetime
import enum
import io
import os
import re
from os import path
from typing import Union, Dict, Callable, Optional

import dateutil.parser
from beancount.core import data
from beancount.core.amount import Amount
from beancount.core.number import D
from beancount.core.number import ZERO
from beancount.ingest import importer
from beancount.utils.date_utils import parse_date_liberally

DEFAULT = "DEFAULT"


# The set of interpretable columns.
class Col(enum.Enum):
    # The settlement date, the date we should create the posting at.
    DATE = '[DATE]'

    # The date at which the transaction took place.
    TXN_DATE = '[TXN_DATE]'

    # The time at which the transaction took place.
    # Beancount does not support time field -- just add it to metadata.
    TXN_TIME = '[TXN_TIME]'

    # The payee field.
    PAYEE = '[PAYEE]'

    # The narration fields. Use multiple fields to combine them together.
    NARRATION = NARRATION1 = '[NARRATION1]'
    NARRATION2 = '[NARRATION2]'
    REMARK = '[REMARK]'

    # The amount being posted.
    AMOUNT = '[AMOUNT]'

    # Debits and credits being posted in separate, dedicated columns.
    AMOUNT_DEBIT = '[DEBIT]'
    AMOUNT_CREDIT = '[CREDIT]'

    # The balance amount, after the row has posted.
    BALANCE = '[BALANCE]'

    # A field to use as a tag name.
    TAG = '[TAG]'

    # A column which says DEBIT or CREDIT (generally ignored).
    DRCR = '[DRCR]'

    # Last 4 digits of the card.
    LAST4 = '[LAST4]'

    # An account name.
    ACCOUNT = '[ACCOUNT]'

    # Transaction status
    STATUS = '[STATUS]'

    # Transcatin type.
    TYPE = "[TYPE]"


# The set of status which says DEBIT or CREDIT
class Drcr(enum.Enum):
    DEBIT = '[DEBIT]'

    CREDIT = '[CREDIT]'

    UNCERTAINTY = '[UNCERTAINTY]'


def cast_to_decimal(amount):
    """Cast the amount to either an instance of Decimal or None.

    Args:
        amount: A string of amount. The format may be '¥1,000.00', '5.20', '200'
    Returns:
        The corresponding Decimal of amount.
    """
    if amount is None:
        return None
    amount = ''.join(amount.split(','))
    numbers = re.findall(r"\d+\.?\d*", amount)
    assert len(numbers) >= 1
    return D(numbers[0])


def strip_blank(contents):
    """
    strip the redundant blank in file contents.
    """
    with io.StringIO(contents) as csvfile:
        csvreader = csv.reader(csvfile, delimiter=",", quotechar='"')
        rows = []
        for row in csvreader:
            rows.append(",".join(['"{}"'.format(x.strip()) for x in row]))
        return "\n".join(rows)


def get_amounts(iconfig: Dict[Col, str], row, DRCR_status: Drcr,
    allow_zero_amounts: bool = False):
    """Get the amount columns of a row.

    Args:
        iconfig: A dict of Col to row index.
        row: A row array containing the values of the given row.
        allow_zero_amounts: Is a transaction with amount D('0.00') okay? If not,
            return (None, None).
    Returns:
        A pair of (debit-amount, credit-amount), both of which are either an
        instance of Decimal or None, or not available.
    """
    debit, credit = None, None
    if Col.AMOUNT in iconfig:
        amount = row[iconfig[Col.AMOUNT]]
        # Distinguish debit or credit
        if DRCR_status == Drcr.CREDIT:
            credit = amount
        else:
            debit = amount
    else:
        debit, credit = [row[iconfig[col]] if col in iconfig else None
                         for col in [Col.AMOUNT_DEBIT, Col.AMOUNT_CREDIT]]

    # If zero amounts aren't allowed, return null value.
    is_zero_amount = (
            (credit is not None and cast_to_decimal(credit) == ZERO) and
            (debit is not None and cast_to_decimal(debit) == ZERO))
    if not allow_zero_amounts and is_zero_amount:
        return None, None

    return (
        -cast_to_decimal(debit) if debit else None,
        cast_to_decimal(credit) if credit else None
    )


def get_debit_or_credit_status(iconfig: [Col, str], row, DRCR_dict):
    """Get the status which says DEBIT or CREDIT of a row.
    """

    try:
        if Col.AMOUNT in iconfig:
            DRCR = DRCR_dict[row[iconfig[Col.DRCR]]]
            return DRCR
        else:
            if Col.AMOUNT_CREDIT in iconfig and row[iconfig[Col.AMOUNT_CREDIT]]:
                return Drcr.CREDIT
            elif Col.AMOUNT_DEBIT in iconfig and row[iconfig[Col.AMOUNT_DEBIT]]:
                return Drcr.DEBIT
            else:
                return Drcr.UNCERTAINTY
    except KeyError:
        return Drcr.UNCERTAINTY


class Importer(importer.ImporterProtocol):
    """Importer for CSV files."""

    def __init__(self,
        config,
        default_account,
        currency,
        file_name_prefix: str,
        skip_lines: int = 0,
        last4_map: Optional[Dict] = None,
        categorizer: Optional[Callable] = None,
        institution: Optional[str] = None,
        debug: bool = False,
        csv_dialect: Union[str, csv.Dialect] = 'excel',
        dateutil_kwds: Optional[Dict] = None,
        narration_sep: str = '; ',
        close_flag: str = '',
        DRCR_dict: Optional[Dict] = None,
        assets_account: Optional[Dict] = None,
        debit_account: Optional[Dict] = None,
        credit_account: Optional[Dict] = None):
        """Constructor.

        Args:
            config: A dict of Col enum types to the names or indexes of the
                columns.
            default_account: An account string, the default account to post
                this to.
            currency: A currency string, the currency of this account.
            skip_lines: Skip first x (garbage) lines of file.
            last4_map: A dict that maps last 4 digits of the card to a friendly
                string.
            categorizer: A callable that attaches the other posting (usually
                expenses) to a transaction with only single posting.
            institution: An optional name of an institution to rename the files
                to.
            debug: Whether or not to print debug information.
            dateutil_kwds: An optional dict defining the dateutil parser kwargs.
            csv_dialect: A `csv` dialect given either as string or as instance
                or subclass of `csv.Dialect`.
            close_flag: A string show the garbage transaction from the STATUS
                column.
            DRCR_dict: An optional dict of Debit_or_credit.DEBIT or
                Debit_or_credit.CREDIT to user-defined debit or credit string
                occurs in the DRCR column. If DRCR column is revealed and
                DRCR_dict is None, the status of trasaction will be uncertain.
            assets_account: An optional dict of user-defined.
        """

        assert isinstance(config, dict)
        self.config = config

        self.default_account = default_account
        self.currency = currency
        self.file_name_prefix = file_name_prefix
        assert isinstance(skip_lines, int)
        self.skip_lines = skip_lines
        self.last4_map = last4_map or {}
        self.debug = debug
        self.dateutil_kwds = dateutil_kwds
        self.csv_dialect = csv_dialect
        self.narration_sep = narration_sep
        self.close_flag = close_flag

        # Reverse the key and value of the DRCR_dict.
        self.DRCR_dict = dict(
            zip(DRCR_dict.values(), DRCR_dict.keys())) if isinstance(DRCR_dict,
                                                                     dict) else {}
        self.assets_account = assets_account if isinstance(assets_account,
                                                           dict) else {}
        self.debit_account = debit_account if isinstance(debit_account,
                                                         dict) else {}
        self.credit_account = credit_account if isinstance(credit_account,
                                                           dict) else {}
        if DEFAULT not in self.assets_account:
            self.assets_account[DEFAULT] = self.default_account
        if DEFAULT not in self.debit_account:
            self.debit_account[DEFAULT] = self.default_account
        if DEFAULT not in self.credit_account:
            self.credit_account[DEFAULT] = self.default_account

        # FIXME: This probably belongs to a mixin, not here.
        self.institution = institution
        self.categorizer = categorizer

    def name(self):
        """Generate an importer name printed out.

        This method provides a unique id for each importer instance. It’s
        convenient to be able to refer to your importers with a unique name;
        it gets printed out by the identification process, for instance.

        Returns:
            A name str.
        """
        return '{}: "{}"'.format(super().name(), self.file_account(None))

    def identify(self, file):
        """Whether the importer can handle the given file.
        
        This method just returns true if this importer can handle the given
        file. You must implement this method, and all the tools invoke it to
        figure out the list of (file, importer) pairs. This function is used
        by bean-identity and bean-extract tools.
        
        Returns:
            A bool to identity whether or not.
        """
        if file.mimetype() != 'text/csv':
            return False
        if not os.path.basename(file.name).startswith(self.file_name_prefix):
            return False

        iconfig, has_header = normalize_config(self.config, file.head(-1),
                                               self.skip_lines)
        if len(iconfig) != len(self.config):
            return False
        return True

    def file_account(self, _):
        """Provide the root account.
        
        This method returns the root account associated with this importer.
        This is where the downloaded file will be moved by the filing script.
        This function is used by bean-file tool.
        
        Returns:
            A root acount name str.
        """
        return self.default_account

    def file_name(self, file):
        """Rename the given file.
        
         It’s most convenient not to bother renaming downloaded files.
         Oftentimes, the files generated from your bank either all have a
         unique name and they end up getting renamed by your browser when you
         download multiple ones and the names collide. This function is used
         for the importer to provide a “nice” name to file the download under.
        
        Returns:
            A new file name str.
        """

        filename = path.splitext(path.basename(file.name))[0]
        if self.institution:
            filename = '{}.{}'.format(self.institution, filename)
        return '{}.csv'.format(filename)

    def file_date(self, file):
        """Get the maximum date from the file.
        
        If a date can be extracted from the statement’s contents, return it
        here. This is useful for dated PDF statements… it’s often possible
        using regular expressions to grep out the date from a PDF converted to
        text. This allows the filing script to prepend a relevant date instead
        of using the date when the file was downloaded (the default).
        
        """
        iconfig, has_header = normalize_config(self.config, file.head(-1),
                                               self.skip_lines)
        if Col.DATE in iconfig:
            reader = iter(csv.reader(open(file.name)))
            for _ in range(self.skip_lines):
                next(reader)
            if has_header:
                next(reader)
            max_date = None
            for row in reader:
                if not row:
                    continue
                if row[0].startswith('#'):
                    continue
                date_str = row[iconfig[Col.DATE]]
                date = parse_date_liberally(date_str, self.dateutil_kwds)
                if max_date is None or date > max_date:
                    max_date = date
            return max_date

    def extract(self, file):
        """Parse and extract Beanount contents from the given file.
        
        This is called to attempt to extract some Beancount directives from the
        file contents. It must create the directives by instantiating the
        objects defined in beancount.core.data and return them. This function
        is used by bean-extract tool.

        Returns:
            A list of beancount.core.data object, and each of them can be
            converted into a command-line accounting.
        """
        entries = []

        # Normalize the configuration to fetch by index.
        iconfig, has_header = normalize_config(self.config, file.head(-1),
                                               self.skip_lines)

        reader = iter(csv.reader(open(file.name), dialect=self.csv_dialect))

        # Skip garbage lines
        for _ in range(self.skip_lines):
            next(reader)

        # Skip header, if one was detected.
        if has_header:
            next(reader)

        def get(row, ftype):
            try:
                return row[iconfig[ftype]] if ftype in iconfig else None
            except IndexError:  # FIXME: this should not happen
                return None

        # Parse all the transactions.
        first_row = last_row = None
        for index, row in enumerate(reader, 1):
            if not row:
                continue
            if row[0].startswith('#'):
                continue
            if row[0].startswith("-----------"):
                break

            # If debugging, print out the rows.
            if self.debug:
                print(row)

            if first_row is None:
                first_row = row
            last_row = row

            # Extract the data we need from the row, based on the configuration.
            status = get(row, Col.STATUS)
            # When the status is CLOSED, the transaction where money had not been paid should be ignored.
            if isinstance(status, str) and status == self.close_flag:
                continue

            # Distinguish debit or credit
            DRCR_status = get_debit_or_credit_status(iconfig, row,
                                                     self.DRCR_dict)

            date = get(row, Col.DATE)
            txn_date = get(row, Col.TXN_DATE)
            txn_time = get(row, Col.TXN_TIME)

            account = get(row, Col.ACCOUNT)
            tx_type = get(row, Col.TYPE)
            tx_type = tx_type or ""

            payee = get(row, Col.PAYEE)
            if payee:
                payee = payee.strip()

            fields = filter(None, [get(row, field)
                                   for field in (Col.NARRATION1,
                                                 Col.NARRATION2)])
            narration = self.narration_sep.join(
                field.strip() for field in fields)

            remark = get(row, Col.REMARK)

            tag = get(row, Col.TAG)
            tags = {tag} if tag is not None else data.EMPTY_SET

            last4 = get(row, Col.LAST4)

            balance = get(row, Col.BALANCE)

            # Create a transaction
            meta = data.new_metadata(file.name, index)
            if txn_date is not None:
                meta['date'] = parse_date_liberally(txn_date,
                                                    self.dateutil_kwds)
            if txn_time is not None:
                meta['time'] = str(dateutil.parser.parse(txn_time).time())
            if balance is not None:
                meta['balance'] = D(balance)
            if last4:
                last4_friendly = self.last4_map.get(last4.strip())
                meta['card'] = last4_friendly if last4_friendly else last4
            date = parse_date_liberally(date, self.dateutil_kwds)
            # flag = flags.FLAG_WARNING if DRCR_status == Debit_or_credit.UNCERTAINTY else self.FLAG
            txn = data.Transaction(
                meta,
                date,
                self.FLAG,
                payee,
                "{}({})".format(narration, remark),
                tags,
                data.EMPTY_SET,
                []
            )

            # Attach one posting to the transaction
            amount_debit, amount_credit = get_amounts(iconfig, row, DRCR_status)

            # Skip empty transactions
            if amount_debit is None and amount_credit is None:
                continue

            for amount in [amount_debit, amount_credit]:
                if amount is None:
                    continue
                units = Amount(amount, self.currency)

                # Uncertain transaction, maybe capital turnover
                if DRCR_status == Drcr.UNCERTAINTY:
                    if remark and len(remark.split("-")) == 2:
                        remarks = remark.split("-")
                        primary_account = mapping_account(self.assets_account,
                                                          remarks[1])
                        secondary_account = mapping_account(self.assets_account,
                                                            remarks[0])
                        txn.postings.append(
                            data.Posting(primary_account, -units, None, None,
                                         None, None))
                        txn.postings.append(
                            data.Posting(secondary_account, None, None, None,
                                         None, None))
                    else:
                        txn.postings.append(
                            data.Posting(self.default_account, units, None,
                                         None, None, None))


                # Debit or Credit transaction
                else:
                    # Primary posting
                    # Rename primary account if remark field matches one of assets account
                    primary_account = mapping_account(self.assets_account,
                                                      remark)
                    txn.postings.append(
                        data.Posting(primary_account, units, None, None, None,
                                     None))

                    # Secondary posting
                    # Rename secondary account by credit account or debit account based on DRCR status
                    payee_narration = payee + narration
                    _account = self.credit_account if DRCR_status == Drcr.CREDIT else self.debit_account
                    secondary_account = mapping_account(_account,
                                                        payee_narration)
                    #                    secondary_account = _account[DEFAULT]
                    #                    for key in _account.keys():
                    #                        if key == DEFAULT:
                    #                            continue
                    #                        if re.search(key, payee_narration):
                    #                            secondary_account = _account[key]
                    #                            break
                    txn.postings.append(
                        data.Posting(secondary_account, None, None, None, None,
                                     None))

            # Attach the other posting(s) to the transaction.
            if isinstance(self.categorizer, collections.Callable):
                txn = self.categorizer(txn)

            # Add the transaction to the output list
            entries.append(txn)

        # Figure out if the file is in ascending or descending order.
        first_date = parse_date_liberally(get(first_row, Col.DATE),
                                          self.dateutil_kwds)
        last_date = parse_date_liberally(get(last_row, Col.DATE),
                                         self.dateutil_kwds)
        is_ascending = first_date < last_date

        # Reverse the list if the file is in descending order
        if not is_ascending:
            entries = list(reversed(entries))

        # Add a balance entry if possible
        if Col.BALANCE in iconfig and entries:
            entry = entries[-1]
            date = entry.date + datetime.timedelta(days=1)
            balance = entry.meta.get('balance', None)
            if balance:
                meta = data.new_metadata(file.name, index)
                entries.append(
                    data.Balance(meta, date,
                                 self.default_account,
                                 Amount(balance, self.currency),
                                 None, None))

        # Remove the 'balance' metadta.
        for entry in entries:
            entry.meta.pop('balance', None)

        return entries


def normalize_config(config, head, skip_lines: int = 0):
    """Using the header line, convert the configuration field name lookups to int indexes.

    Args:
      config: A dict of Col types to string or indexes.
      head: A string, some decent number of bytes of the head of the file.
      skip_lines: Skip first x (garbage) lines of file.
    Returns:
      A pair of
        A dict of Col types to integer indexes of the fields, and
        a boolean, true if the file has a header.
    Raises:
      ValueError: If there is no header and the configuration does not consist
        entirely of integer indexes.
    """
    assert isinstance(skip_lines, int)
    assert skip_lines >= 0
    for _ in range(skip_lines):
        head = head[head.find("\n") + 1:]

    strip_blank(head)
    has_header = csv.Sniffer().has_header(head)
    if has_header:
        header = next(csv.reader(io.StringIO(head)))
        field_map = {field_name.strip(): index
                     for index, field_name in enumerate(header)}
        index_config = {}
        for field_type, field in config.items():
            if isinstance(field, str):
                try:
                    field = field_map[field]
                except KeyError as e:
                    print(e)
                    break
            index_config[field_type] = field
    else:
        if any(not isinstance(field, int)
               for field_type, field in config.items()):
            raise ValueError("CSV config without header has non-index fields: "
                             "{}".format(config))
        index_config = config
    return index_config, has_header


def mapping_account(account_map, keyword):
    """Finding which key of account_map contains the keyword, return the corresponding value.

    Args:
      account_map: A dict of account keywords string (each keyword separated by "|") to account name.
      keyword: A keyword string.
    Return:
      An account name string.
    Raises:
      KeyError: If "DEFAULT" keyword is not in account_map.
    """
    if DEFAULT not in account_map:
        raise KeyError("DEFAULT is not in " + account_map.__str__)
    account_name = account_map[DEFAULT]
    for account_keywords in account_map.keys():
        if account_keywords == DEFAULT:
            continue
        if re.search(account_keywords, keyword):
            account_name = account_map[account_keywords]
            break
    return account_name

#!/usr/bin/env python3
import sys

from beancount.core.data import Transaction

sys.path.append("./importers")
from importers.beanmaker import Drcr, Col, Importer

# Col为枚举类型，预定义了每笔交易记录所需要的内容，_config_alipay负责定义枚举内容与csv表头之间的对应关系

_config_alipay = {
    Col.DATE: "交易创建时间",
    Col.PAYEE: "交易对方",
    Col.NARRATION: "商品名称",
    Col.REMARK: "备注",
    Col.AMOUNT: "金额（元）",
    Col.DRCR: "收/支",
    Col.STATUS: "资金状态",
    Col.TXN_TIME: "交易创建时间",
    Col.TXN_DATE: "交易创建时间",
    Col.TYPE: "类型",
}

_config_wechat = {
    Col.DATE: "交易时间",
    Col.PAYEE: "交易对方",
    Col.NARRATION: "商品",
    Col.REMARK: "支付方式",
    Col.AMOUNT: "金额(元)",
    Col.DRCR: "收/支",
    Col.STATUS: "当前状态",
    Col.TXN_TIME: "交易时间",
    Col.TXN_DATE: "交易时间",
    Col.TYPE: "交易类型",
}

# _default_account负责定义默认账户
_default_account_alipay = "Assets:Alipay:Balance"

_default_account_wechat = "Assets:WeChat:Balance"

_default_account_comm = "Liabilities:CreditCard:BOC:CN"

# _currency定义货币单位
_currency = "CNY"

# Debit_or_credit也是枚举类型，预定义了支出和收入两类，_DRCR_dict负责定义这两类与csv中能够表明该状态的文本之间的对应关系
_DRCR_dict = {
    Drcr.DEBIT: "支出",
    Drcr.CREDIT: "收入"
}

common_assets_account = {
    "交通银行|2222": "Liabilities:CreditCard:BOC"
}

# _assets_account负责保存账户信息，key为手工对账时在备注中输入的关键词；
# 关键词中，"DEFAULT"为非必选项，不提供时将以"_default_account_xxx"的属性值作为"DEFAULT"对应的值；
# 多个关键词用竖线分割，只要备注中出现该关键词，就把该交易分类到对应账户下。
_wechat_assets_account = {
    "DEFAULT": "Assets:WeChat:Balance",
    "招行信用卡|0000": "Liabilities:CreditCard:CMB",
    "招商银行": "Assets:DebitCard:CMB",
    "交通信用卡银行|2222": "Liabilities:CreditCard:BOC:CN",
    "中信银行": "Liabilities:CreditCard:CITIC",
    "汇丰银行": "Liabilities:CreditCard:HSBC:CN",
    "支付宝": "Assets:VirtualCard:Alipay",
    "余额宝": "Assets:MoneyFund:Yuebao",
    "零钱|微信": "Assets:WeChat:Balance"
}
_wechat_assets_account.update(common_assets_account)

# _debit_account负责保存支出账户信息，key为与该账户相关的关键词；
# 关键词中，"DEFAULT"为非必选项，不提供时将以"_default_account_xxx"的属性值作为"DEFAULT"对应的值；
# 多个关键词用竖线分割，只要当交易为“支出”，且交易对方名称和商品名称中出现该关键词，就把该交易分类为对应支出。
_debit_account = {
    "DEFAULT": "Expenses:Food:Other",
    "iCloud|腾讯云|阿里云|Plex": "Expenses:Fun:Subscription",
    "滴滴|司机": "Expenses:Transport:Taxi",
    "天和亿|单车": "Expenses:Transport:Bike",
    "中国铁路": "Expenses:Transport:Railway",
    "卡表充值|燃气": "Expenses:House:Gas",
    "友宝|芬达|雪碧|可乐|送水|怡宝|饮料|美年达|售货机": "Expenses:Food:Drinks",
    "水果": "Expenses:Food:Fruits",
    "买菜|叮咚|美团买菜": "Expenses:Food:Cooking",
    "泰餐": "Expenses:Food:Restaurant",
    "App Store|Steam|会员": "Expenses:Fun:Software",
    "全时|华联|家乐福|超市|红旗|WOWO|百货|伊藤|永旺|全家": "Expenses:Daily:Commodity",
    "汽车票|蒜芽信息科技|优步|火车|动车|空铁无忧网|滴滴|汽车|运输|机场|航空|机票|高铁|出行|车费|打车": "Expenses:Travel",
    "捐赠": "Expenses:PublicWelfare",
    "话费|流量|手机|中国移动": "Expenses:Daily:PhoneCharge",
    "电影|大麦网|演出|淘票票": "Expenses:Fun:Amusement",
    "地铁|轨道交通": "Expenses:Transport:Public",
    "青桔|骑安": "Expenses:Transport:Bike",
    "衣|裤|鞋": "Expenses:Dressup:Clothing",
    "造型|美发|理发": "Expenses:Dressup:Hair",
    "化妆品": "Expenses:Dressup:Cosmetic",
    "医院|药房": "Expenses:Health:Hospital",
    "酒店|airbnb": "Expenses:Travel:Hotel",
    "机票|高铁|票务|特快|火车票|飞机票": "Expenses:Travel:Fare",
    "借款": "Assets:Receivables",
    "蚂蚁财富": "Assets:MoneyFund:BondFund",
    '签证': "Expenses:Travel:Visa",
    "门票": "Expenses:Travel:Ticket",
    "gopro|键盘|电脑|手机|SD卡|相机|MacBook|boox|ipad|apple|oneplus": "Expenses:Digital",
    "快递": "Expenses:Daily",
    'PLAYSTATION': "Expenses:Fun:Game",
}

# _credit_account负责保存收入账户信息，key为与该账户相关的关键词
# 关键词中，"DEFAULT"为非必选项，不提供时将以"_default_account_xxx"的属性值作为"DEFAULT"对应的值；
# 多个关键词用竖线分割，只要当交易为“收入”，且交易对方名称和商品名称中出现该关键词，就把该交易分类为对应收入。
_credit_account = {"DEFAULT": "Income:RedPacket", "借款": "Assets:Receivables"}

wechat_config = Importer(
    config=_config_wechat,
    default_account=_default_account_wechat,
    currency=_currency,
    file_name_prefix='微信支付账单',
    skip_lines=0,
    DRCR_dict=_DRCR_dict,
    assets_account=_wechat_assets_account,
    debit_account=_debit_account,
    credit_account=_credit_account
)

_alipay_assets_account = {
    "DEFAULT": "Assets:Alipay:Balance",
    "花呗": "Liabilities:VirtualCard:Huabei",
}
_alipay_assets_account.update(common_assets_account)

alipay_config = Importer(
    config=_config_alipay,
    default_account=_default_account_alipay,
    currency=_currency,
    file_name_prefix='alipay_record',
    skip_lines=0,
    DRCR_dict=_DRCR_dict,
    assets_account=_alipay_assets_account,
    debit_account=_debit_account,
    credit_account=_credit_account
)

_comm_assets_account = {
    "DEFAULT": "Liabilities:CreditCard:BOC:CN"
}
_comm_assets_account.update(common_assets_account)

from beancount.ingest.importers import csv

# 信用卡
_config_com = {
    csv.Col.DATE: "记账日期",
    csv.Col.PAYEE: "交易说明",
    csv.Col.NARRATION: "交易说明",
    csv.Col.AMOUNT_DEBIT: "交易金额",
    csv.Col.TXN_DATE: "交易日期",
    csv.Col.LAST4: "卡末四位",
}


def comm_categorizer(txn: Transaction):
    # At this time the txn has only one posting
    try:
        posting1 = txn.postings[0]
    except IndexError:
        return txn

    from importers.beanmaker import mapping_account
    account_name = mapping_account(_debit_account, txn.narration)

    posting2 = posting1._replace(
        account=account_name,
        units=-posting1.units
    )
    # Insert / Append the posting into the transaction
    if posting1.units < posting2.units:
        txn.postings.append(posting2)
    else:
        txn.postings.insert(0, posting2)

    return txn


comm_config = csv.Importer(
    config=_config_com,
    account=_default_account_comm,
    currency=_currency,
    last4_map={"2222": "优逸白"},
    categorizer=comm_categorizer
)

CONFIG = [
    wechat_config,
    alipay_config,
    comm_config,
]

├── README.md
├── account
│   ├── assets.bean
│   ├── crypto.bean
│   ├── equity.bean
│   ├── expenses.bean
│   ├── income.bean
│   ├── liabilities.bean
│   ├── securities.bean
│   └── vesting.bean
├── beans
│   ├── 2020.bean
│   ├── 2021
│   │   ├── 01.bean
│   │   ├── 02.bean
│   │   ├── 03.bean
│   │   └── 04.bean
│   ├── 2021.bean
│   ├── alipay_record_20190101_20191231.bean
│   ├── alipay_record_20200101_20201231.bean
│   ├── assets-broker.bean
│   ├── comm-2021.01.bean
│   ├── comm-2021.02.bean
│   ├── comm-2021.03.bean
│   ├── 微信支付账单(20200701-20200930).bean
│   └── 微信支付账单(20201001-20201231).bean
├── config.py
├── datas
│   ├── alipay_record_20190101_20191231.csv
│   ├── alipay_record_20200101_20201231.csv
│   ├── comm-2021.01.csv
│   ├── comm-2021.02.csv
│   ├── comm-2021.03.csv
│   ├── 微信支付账单(20200701-20200930).csv
│   └── 微信支付账单(20201001-20201231).csv
├── importers
│   └── beanmaker.py
├── main.bean
├── processing.sh
├── requirements.txt
└── strip_blank.py

微信支付账单明细,,,,,,,,
微信昵称：[xxx],,,,,,,,
起始时间：[2018-01-01 00:00:00] 终止时间：[2018-03-31 23:59:59],,,,,,,,
导出类型：[全部],,,,,,,,
导出时间：[2020-02-28 12:59:49],,,,,,,,
,,,,,,,,
共207笔记录,,,,,,,,
收入：137笔 xxxx.34元,,,,,,,,
支出：66笔 xxxx.60元,,,,,,,,
中性交易：4笔 xxxx.13元,,,,,,,,
注：,,,,,,,,
1. 充值/提现/理财通购买/零钱通存取/信用卡还款等交易，将计入中性交易,,,,,,,,
2. 本明细仅展示当前账单中的交易，不包括已删除的记录,,,,,,,,
3. 本明细仅供个人对账使用,,,,,,,,
,,,,,,,,
----------------------微信支付账单明细列表--------------------,,,,,,,,
交易时间,交易类型,交易对方,商品,收/支,金额(元),支付方式,当前状态,交易单号,商户单号,备注
2018-03-31 21:35:09,微信红包,/,"/",支出,¥100.00,零钱,支付成功,1000039501180331000xxxxxxxxxxxxxxxxx	,10000395012018033xxxxxxxxxxxxxx	,"/"

:set fileencoding=utf-8
:w

支付宝交易记录明细查询
账号:[xxxxxxxx@xxxxx.com]
起始日期:[2019-01-01 00:00:00]    终止日期:[2020-01-01 00:00:00]
---------------------------------交易记录明细列表------------------------------------
交易号                  ,商家订单号               ,交易创建时间              ,付款时间                ,最近修改时间              ,交易来源地     ,类型              ,交易对方            ,商品名称                ,金额（元）   ,收/支     ,交易状态    ,服务费（元）   ,成功退款（元）  ,备注                  ,资金状态     ,
2019123122001456xxxxxxxxxxxx	,M201912317xxxxxxx   	,2019-12-31 13:26:28 ,2019-12-31 13:26:29 ,2019-12-31 13:26:29 ,其他（包括阿里巴巴和外部商家）,即时到账交易          ,中国铁路网络有限公司      ,火车票                 ,493.50  ,支出      ,交易成功    ,0.00     ,0.00     ,                    ,已支出      ,
20191231343073829431 	,                    	,2019-12-31 05:39:17 ,                    ,2019-12-31 05:39:17 ,支付宝网站     ,即时到账交易          ,博时基金管理有限公司      ,余额宝-2019.12.30-收益发放 ,2.83    ,        ,交易成功    ,0.00     ,0.00     ,                    ,已收入      ,

├── account
│   ├── assets.bean
│   ├── equity.bean
│   ├── expenses.bean
│   ├── income.bean
│   ├── liabilities.bean
├── beans
│   ├── 2020.bean
│   ├── 2021
│   │   ├── 01.bean
│   │   ├── 02.bean
│   │   ├── 03.bean
│   │   └── 04.bean
│   ├── 微信\224\230账\215\225(20200701-20200930).bean
│   └── 微信\224\230账\215\225(20201001-20201231).bean
├── config.py
├── datas
│   ├── 微信\224\230账\215\225(20200701-20200930).csv
│   └── 微信\224\230账\215\225(20201001-20201231).csv
├── importers
│   └── beanmaker.py
├── main.bean
├── processing.sh
├── requirements.txt

option "title" "ledger" ; "我的账本" ledger
option "operating_currency" "CNY" ; 帐本货币
option "operating_currency" "USD"

; fava
2016-04-14 custom "fava-option" "auto-reload" "true"

include "account/*.bean"
include "beans/*.bean"

; 现金
2010-11-11 open Assets:Cash

; 支付宝
2015-11-11 open Assets:Alipay:Balance ;"余额"

; 微信余额
2010-01-01 open Assets:WeChat:Balance

; 老虎证券
2018-06-01 open Assets:Broker:US:Tiger

; 银行账户来
2010-11-11 open Assets:DebitCard:CMB CNY

; 欠的钱
2000-01-01 open Assets:Receivables:Zhangsan CNY

2000-03-09 * "借钱给张三 100000"
  Assets:Receivables:Zhangsan 10000 CNY
  Assets:DebitCard:CMB   -10000 CNY

2001-01-01 close Assets:Receivables:Zhangsan

2010-11-11 open Income:Salary:Hooli CNY  	; "Regular Pay"
2010-11-11 open Income:Bonus:Hooli  CNY 	; "Annual bonus"

Food & Drinks
    Bar, cafe
    Groceries
    Restaurant, fast-food
Shopping
    Clothes & shoes
    Drug-store chemist
    Gifts
    Jewels
    Pets
    Stationery
Housing
    Energy
    Maintenance
    Mortgage
    Property insurance
    Rent
    Services
Transportation
    Business trips
    Long distance
    Public transport
    Taxi
Vehicle
    Fuel
    Leasing
    Parking
    Rentals
    Vehicle insurance
    Vehicle maintenance
Life & Entertainment
    Sport
    fitness
    Alcohol
    Book, audio, subscriptions
    Charity
    Wellness
Communication
    Internet
    Phone
    Postal Services
    Software

Automobile
  Accessories
  Car Insurance
  Gas/Fuel
  Lease
  Maintenance
  Other
  Parking
Bills
  Cable
  Electricity
  Gas
  Internet/Broadband
  Mobile Phone
  Other
  Phone
  Water
Clothing
  Accessories
  Clothes
  Jewelry
  Other
  Shoes
Digital
  Apps
  Books
  Movies
  Music
  Other
  Podcasts
  TV Shows
Food & Dining
  Dining/Eating Out
  Groceries
  Other
Health Care
  Dental
  Eye Care
  Health Insurance
  Medical
  Other
  Pharmacy
Housing
  Furniture/Accessories
  Home Insurance
  Maintenance
  Mortgage
  Other
  Rent
Leisure
  Entertainment
  Fitness/Sport
  Other
  Personal Care
Loans
  Other
  Taxes
  Transportation
  Travel

; 衣、鞋
2010-01-01 open Expenses:Dressup:Clothing

; 食
2010-01-01 open Expenses:Food:Drinks ;"饮料"
2010-01-01 open Expenses:Food:Fruits ;"水果"

; 住
2010-11-11 open Expenses:House:Rent              ; 房租
2010-11-11 open Expenses:House:WaterElectricity     ; 水费、电费
2010-01-01 open Expenses:House:Gas ;"燃气"

; 行
2010-11-11 open Expenses:Transport:Public
2010-11-11 open Expenses:Transport:Taxi

; other
2010-01-01 open Expenses:Digital

2010-11-11 open Liabilities:CreditCard:BOC CNY

; 欠钱
2000-01-01 open Liabilities:Payables:Zhangsan CNY

Expenses (all types)
  1. Rent/Mortgage
      a. Home Owners Association Dues
      b. Rental Insurance
      c. Home Owners Insurance
  2. Fixed Expenses
      a. Utilities
      b. Gas
      c. Electric
      d. Water/Trash/Sewer
      e. Cable/Internet/Phone
      f. Cell Phone
      g. Credit Cards
      h. Car Expenses
      i. Maintenance
      j. Gas
  3. Extra Expenses
      a. Grocery (Food)
      b. Clothes/Shoes/Hygiene
      c. Extra for Home Expenses
  4. Savings
      a. Savings Account. Speak with employer; some saving plans can pull from paycheck before taxes. That means less of your paycheck is taxable.
      b. Create an Emergency Fund; it should be at least 6 months of expenses. Emergencies can happen and drain a well-established savings account
  5. Taxes
      a. No explanation needed
  6. Fun Cash
      a. Out with friends
      b. Movies
      c. Vacations

  Adjustment
  Auto
      Fees
      Gas
      Parking
      Repair and Maintenance
  Bank Service Charge
  Books
  Cable
  Charity
  Clothes
  Computer
  Dining
  Education
  Entertainment
      Music/Movies
      Recreation
      Travel
  Gifts
  Groceries
  Hobbies
  Insurance
      Auto Insurance
      Health Insurance
      Life Insurance
  Laundry/Dry Cleaning
  Medical Expenses
  Miscellaneous
  Online Services
  Phone
  Public Transportation
  Subscriptions
  Supplies
  Taxes
      Federal
      Medicare
      Other Tax
      Social Security
      State/Province
  Utilities
      Electric
      Garbage collection
      Gas
      Water

option "operating_currency" "CNY" ; 帐本货币
option "operating_currency" "USD"

2010-11-11 open Assets:DebitCard:CMB CNY
  name: "招商银行借记卡"

2010-01-01 open Income:Salary:Company CNY

;开户，支持 Unicode, yyyy-MM-dd 表示开户时间
yyyy-MM-dd open 账户类型:命名:命名区别 货币[,货币2]

2016-01-02 * "Income"
  Income:Salary:Company -1234 CNY
  Assets:DebitCard:CMB

2020-01-01 close Assets:DebitCard:CMB

2010-01-01 open Expenses:Drink:Coffee
2010-01-01 open Liabilities:CreditCard:CMB

2021-01-01 * "收付款方：某某咖啡店" "备注：Coffee"
  Expenses:Drink:Coffee        +40.00 CNY
  Liabilities:CreditCard:CMB

[yyyy-MM-dd] [*|!] "payee" "备注"
  [account1]          +[num] [currency-unit]
  [account2]          (-[num] [currency-unit])

2015-05-30 ! "Cable Co" "Phone Bill" #tag ^link
  id: "TW378743437"               ; Meta-data
  Expenses:Home:Phone  87.45 USD
  Assets:Checking                 ; You may leave one amount out

 (Assets + Expenses) + (Liabilities + Income) + Equity = 0

2010-11-11 open Expenses:Transport:Taxi

2010-11-11 open Expenses:Transport:Public
2010-11-11 open Expenses:Transport:Taxi
2010-11-11 open Expenses:Transport:Bike

2020-02-01 * "北京某有限公司" "工资"
  Income:Salary           -5000 CNY
  Expenses:Endowment      +1000 CNY; 养老保险
  Expenses:Unemployment     +30 CNY; 失业保险
  Expenses:Medical         +300 CNY; 医疗保险
  Expenses:Taxes           +100 CNY; 个人所得税
  Income:HousingFund       -500 CNY; 公司额外支付的住房公积金
  Assets:HousingFund      +1000 CNY; 住房公积金
  Assets:DebitCard:CMB    +3070 CNY; 招商银行工资卡

2020-02-29 * "超市" "食材 牛奶"
  Liabilities:CreditCard:BOC     -90 CNY; 交通银行信用卡
  Expenses:Food:Ingredients      +40 CNY; 食材
  Expenses:Food:Drinks           +50 CNY; 饮品

    2021-01-05 * "信用卡还款"
      Assets:DebitCard:CMB           -100 CNY
      Liabilities:CreditCard:BOCOM   +100 CNY

2021-09-25 * "购汇 还款"
  Liabilities:CreditCard:BOC:US              152 USD @ 6.461381579 CNY
  Assets:DebitCard:CMB                        -982.13 CNY

2019-10-12 * "合租交燃气费用"
  Expenses:House:Gas         +200 CNY
  Liabilities:CreditCard:BOC -200 CNY
  Assets:WeChatPay         +150 CNY; 发回来的红包

pushtag #trip-to-japan
...
poptag #trip-to-japan

fava main.bean

<dependency>
    <groupId>net.sf.json-lib</groupId>
    <artifactId>json-lib</artifactId>
    <version>2.2.2</version>
    <classifier>jdk15</classifier>
</dependency>

<dependency>
    <groupId>net.sf.json-lib</groupId>
    <artifactId>json-lib</artifactId>
    <version>2.2.2</version>
    <classifier>jdk13</classifier>
</dependency>

    <dependency>
       <groupId>com.google.inject</groupId>
       <artifactId>guice</artifactId>
       <version>4.2.1</version>
       <classifier>no_aop</classifier>
     </dependency>

<plugin>
   <groupId>org.apache.maven.plugins</groupId>
   <artifactId>maven-jar-plugin</artifactId>
   <version>3.0.2</version>
   <configuration>
       <classifier>${classifier}</classifier>
   </configuration>
</plugin>

mvn org.apache.maven.plugins:maven-deploy-plugin:3.0.0:deploy-file -Durl=http://localhost:8081/repomanager/ \
                                                                            -DrepositoryId=some.id \
                                                                            -Dfile=path/to/artifact-name-1.0.jar \
                                                                            -DpomFile=path-to-your-pom.xml \
                                                                            -Dfiles=path/to/artifact-name-1.0-debug.jar,path/to/site.pdf \
                                                                            -Dclassifiers=debug,site \
                                                                            -Dtypes=jar,pdf

Caused by: java.lang.NoSuchMethodError: org.apache.commons.lang3.reflect.FieldUtils.getFieldsWithAnnotatio
n(Ljava/lang/Class;Ljava/lang/Class;)[Ljava/lang/reflect/Field;
        at com.opencsv.bean.AbstractMappingStrategy.loadRecursiveClasses(AbstractMappingStrategy.java:498)
        at com.opencsv.bean.AbstractMappingStrategy.loadFieldMap(AbstractMappingStrategy.java:440)
        at com.opencsv.bean.AbstractMappingStrategy.setType(AbstractMappingStrategy.java:363)
        at com.opencsv.bean.util.OpencsvUtils.determineMappingStrategy(OpencsvUtils.java:79)
        at com.opencsv.bean.CsvToBeanBuilder.build(CsvToBeanBuilder.java:234)

source:
category:
tag: 
time:  

source:
category:
tag: 
time: