summaryrefslogtreecommitdiff
path: root/src/csv.cc
diff options
context:
space:
mode:
authorJohn Wiegley <johnw@newartisans.com>2010-03-17 06:22:43 -0400
committerJohn Wiegley <johnw@newartisans.com>2010-03-17 06:22:43 -0400
commit7ca8149ec5c7fa88d98df83e6260210372223036 (patch)
tree4c5741d682e89b1ea4e567c32a78d32ba17737db /src/csv.cc
parent3bb4cb6b6055f180112f357cf23463a1b8c186c5 (diff)
parent8dd362b57cf2b49c5268e72898ae873522d8756f (diff)
downloadfork-ledger-7ca8149ec5c7fa88d98df83e6260210372223036.tar.gz
fork-ledger-7ca8149ec5c7fa88d98df83e6260210372223036.tar.bz2
fork-ledger-7ca8149ec5c7fa88d98df83e6260210372223036.zip
Merge branch 'next'
Diffstat (limited to 'src/csv.cc')
-rw-r--r--src/csv.cc298
1 files changed, 298 insertions, 0 deletions
diff --git a/src/csv.cc b/src/csv.cc
new file mode 100644
index 00000000..5a74232f
--- /dev/null
+++ b/src/csv.cc
@@ -0,0 +1,298 @@
+/*
+ * Copyright (c) 2003-2010, John Wiegley. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * - Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ *
+ * - Neither the name of New Artisans LLC nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <system.hh>
+
+#include "csv.h"
+#include "xact.h"
+#include "post.h"
+#include "account.h"
+#include "journal.h"
+#include "pool.h"
+
+namespace ledger {
+
+string csv_reader::read_field(std::istream& in)
+{
+ string field;
+
+ char c;
+ if (in.peek() == '"' || in.peek() == '|') {
+ in.get(c);
+ char x;
+ while (in.good() && ! in.eof()) {
+ in.get(x);
+ if (x == '\\') {
+ in.get(x);
+ }
+ else if (x == '"' && in.peek() == '"') {
+ in.get(x);
+ }
+ else if (x == c) {
+ if (x == '|')
+ in.unget();
+ else if (in.peek() == ',')
+ in.get(c);
+ break;
+ }
+ if (x != '\0')
+ field += x;
+ }
+ }
+ else {
+ while (in.good() && ! in.eof()) {
+ in.get(c);
+ if (c == ',')
+ break;
+ if (c != '\0')
+ field += c;
+ }
+ }
+ trim(field);
+ return field;
+}
+
+char * csv_reader::next_line(std::istream& in)
+{
+ static char linebuf[MAX_LINE + 1];
+
+ while (in.good() && ! in.eof() && in.peek() == '#')
+ in.getline(linebuf, MAX_LINE);
+
+ if (! in.good() || in.eof())
+ return NULL;
+
+ in.getline(linebuf, MAX_LINE);
+
+ return linebuf;
+}
+
+void csv_reader::read_index(std::istream& in)
+{
+ char * line = next_line(in);
+ if (! line)
+ return;
+
+ std::istringstream instr(line);
+
+ while (instr.good() && ! instr.eof()) {
+ string field = read_field(instr);
+ names.push_back(field);
+
+ if (date_mask.match(field))
+ index.push_back(FIELD_DATE);
+ else if (date_eff_mask.match(field))
+ index.push_back(FIELD_DATE_EFF);
+ else if (code_mask.match(field))
+ index.push_back(FIELD_CODE);
+ else if (payee_mask.match(field))
+ index.push_back(FIELD_PAYEE);
+ else if (amount_mask.match(field))
+ index.push_back(FIELD_AMOUNT);
+ else if (cost_mask.match(field))
+ index.push_back(FIELD_COST);
+ else if (total_mask.match(field))
+ index.push_back(FIELD_TOTAL);
+ else if (note_mask.match(field))
+ index.push_back(FIELD_NOTE);
+ else
+ index.push_back(FIELD_UNKNOWN);
+
+ DEBUG("csv.parse", "Header field: " << field);
+ }
+}
+
+xact_t * csv_reader::read_xact(journal_t& journal, account_t * bucket)
+{
+ restart:
+ char * line = next_line(in);
+ if (! line || index.empty())
+ return NULL;
+
+ std::istringstream instr(line);
+
+ std::auto_ptr<xact_t> xact(new xact_t);
+ std::auto_ptr<post_t> post(new post_t);
+
+ xact->set_state(item_t::CLEARED);
+
+ xact->pos = position_t();
+ xact->pos->pathname = "jww (2010-03-05): unknown";
+ xact->pos->beg_pos = in.tellg();
+ xact->pos->beg_line = 0;
+ xact->pos->sequence = 0;
+
+ post->xact = xact.get();
+
+#if 0
+ post->pos = position_t();
+ post->pos->pathname = pathname;
+ post->pos->beg_pos = line_beg_pos;
+ post->pos->beg_line = linenum;
+ post->pos->sequence = context.sequence++;
+#endif
+
+ post->set_state(item_t::CLEARED);
+ post->account = NULL;
+
+ int n = 0;
+ amount_t amt;
+ string total;
+
+ while (instr.good() && ! instr.eof()) {
+ string field = read_field(instr);
+
+ switch (index[n]) {
+ case FIELD_DATE:
+ if (field.empty())
+ goto restart;
+ try {
+ xact->_date = parse_date(field);
+ }
+ catch (date_error&) {
+ goto restart;
+ }
+ break;
+
+ case FIELD_DATE_EFF:
+ xact->_date_eff = parse_date(field);
+ break;
+
+ case FIELD_CODE:
+ if (! field.empty())
+ xact->code = field;
+ break;
+
+ case FIELD_PAYEE: {
+ bool found = false;
+ foreach (payee_mapping_t& value, journal.payee_mappings) {
+ DEBUG("csv.mappings", "Looking for payee mapping: " << value.first);
+ if (value.first.match(field)) {
+ xact->payee = value.second;
+ found = true;
+ break;
+ }
+ }
+ if (! found)
+ xact->payee = field;
+ break;
+ }
+
+ case FIELD_AMOUNT: {
+ std::istringstream amount_str(field);
+ amt.parse(amount_str, PARSE_NO_REDUCE);
+ if (! amt.has_commodity() &&
+ commodity_pool_t::current_pool->default_commodity)
+ amt.set_commodity(*commodity_pool_t::current_pool->default_commodity);
+ post->amount = amt;
+ break;
+ }
+
+ case FIELD_COST: {
+ std::istringstream amount_str(field);
+ amt.parse(amount_str, PARSE_NO_REDUCE);
+ if (! amt.has_commodity() &&
+ commodity_pool_t::current_pool->default_commodity)
+ amt.set_commodity
+ (*commodity_pool_t::current_pool->default_commodity);
+ post->cost = amt;
+ break;
+ }
+
+ case FIELD_TOTAL:
+ total = field;
+ break;
+
+ case FIELD_NOTE:
+ xact->note = field;
+ break;
+
+ case FIELD_UNKNOWN:
+ if (! names[n].empty() && ! field.empty())
+ xact->set_tag(names[n], field);
+ break;
+ }
+ n++;
+ }
+
+#if 0
+ xact->set_tag(_("Imported"),
+ string(format_date(CURRENT_DATE(), FMT_WRITTEN)));
+ xact->set_tag(_("Original"), string(line));
+ xact->set_tag(_("SHA1"), string(sha1sum(line)));
+#endif
+
+ // Translate the account name, if we have enough information to do so
+
+ foreach (account_mapping_t& value, journal.account_mappings) {
+ if (value.first.match(xact->payee)) {
+ post->account = value.second;
+ break;
+ }
+ }
+
+ xact->add_post(post.release());
+
+ // Create the "balancing post", which refers to the account for this data
+
+ post.reset(new post_t);
+
+ post->xact = xact.get();
+
+#if 0
+ post->pos = position_t();
+ post->pos->pathname = pathname;
+ post->pos->beg_pos = line_beg_pos;
+ post->pos->beg_line = linenum;
+ post->pos->sequence = context.sequence++;
+#endif
+
+ post->set_state(item_t::CLEARED);
+ post->account = bucket;
+
+ if (! amt.is_null())
+ post->amount = - amt;
+
+ if (! total.empty()) {
+ std::istringstream assigned_amount_str(total);
+ amt.parse(assigned_amount_str, PARSE_NO_REDUCE);
+ if (! amt.has_commodity() &&
+ commodity_pool_t::current_pool->default_commodity)
+ amt.set_commodity(*commodity_pool_t::current_pool->default_commodity);
+ post->assigned_amount = amt;
+ }
+
+ xact->add_post(post.release());
+
+ return xact.release();
+}
+
+} // namespace ledger