summaryrefslogtreecommitdiffstats
path: root/plugins/mmutf8fix/mmutf8fix.c
blob: a1a1ee3bc03a763ad9b3f09032fa072efb7cfb3a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
/* mmutf8fix.c
 * fix invalid UTF8 sequences. This is begun as a very simple replacer
 * of non-control characters, and actually breaks some UTF-8 encoding
 * right now. If the module turns out to be useful, it should be enhanced
 * to support modes that really detect invalid UTF8. In the longer term
 * it could also be evolved into an any-charset-to-UTF8 converter. But
 * first let's see if it really gets into widespread enough use.
 *
 * Copyright 2013-2016 Adiscon GmbH.
 *
 * This file is part of rsyslog.
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *       http://www.apache.org/licenses/LICENSE-2.0
 *       -or-
 *       see COPYING.ASL20 in the source distribution
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
#include "config.h"
#include "rsyslog.h"
#include <stdio.h>
#include <stdarg.h>
#include <stdlib.h>
#include <string.h>
#include <assert.h>
#include <signal.h>
#include <errno.h>
#include <unistd.h>
#include <stdint.h>
#include "conf.h"
#include "syslogd-types.h"
#include "srUtils.h"
#include "template.h"
#include "module-template.h"
#include "errmsg.h"

MODULE_TYPE_OUTPUT
MODULE_TYPE_NOKEEP
MODULE_CNFNAME("mmutf8fix")


DEF_OMOD_STATIC_DATA

/* define operation modes we have */
#define MODE_CC 0	 /* just fix control characters */
#define MODE_UTF8 1	 /* do real UTF-8 fixing */

/* config variables */
typedef struct _instanceData {
	uchar replChar;
	uint8_t mode;		/* operations mode */
} instanceData;

typedef struct wrkrInstanceData {
	instanceData *pData;
} wrkrInstanceData_t;

struct modConfData_s {
	rsconf_t *pConf;	/* our overall config object */
};
static modConfData_t *loadModConf = NULL;/* modConf ptr to use for the current load process */
static modConfData_t *runModConf = NULL;/* modConf ptr to use for the current exec process */


/* tables for interfacing with the v6 config system */
/* action (instance) parameters */
static struct cnfparamdescr actpdescr[] = {
	{ "mode", eCmdHdlrGetWord, 0 },
	{ "replacementchar", eCmdHdlrGetChar, 0 }
};
static struct cnfparamblk actpblk =
	{ CNFPARAMBLK_VERSION,
	  sizeof(actpdescr)/sizeof(struct cnfparamdescr),
	  actpdescr
	};

BEGINbeginCnfLoad
CODESTARTbeginCnfLoad
	loadModConf = pModConf;
	pModConf->pConf = pConf;
ENDbeginCnfLoad

BEGINendCnfLoad
CODESTARTendCnfLoad
ENDendCnfLoad

BEGINcheckCnf
CODESTARTcheckCnf
ENDcheckCnf

BEGINactivateCnf
CODESTARTactivateCnf
	runModConf = pModConf;
ENDactivateCnf

BEGINfreeCnf
CODESTARTfreeCnf
ENDfreeCnf


BEGINcreateInstance
CODESTARTcreateInstance
ENDcreateInstance


BEGINcreateWrkrInstance
CODESTARTcreateWrkrInstance
ENDcreateWrkrInstance


BEGINisCompatibleWithFeature
CODESTARTisCompatibleWithFeature
ENDisCompatibleWithFeature


BEGINfreeInstance
CODESTARTfreeInstance
ENDfreeInstance


BEGINfreeWrkrInstance
CODESTARTfreeWrkrInstance
ENDfreeWrkrInstance


static inline void
setInstParamDefaults(instanceData *pData)
{
	pData->mode = MODE_UTF8;
	pData->replChar = ' ';
}

BEGINnewActInst
	struct cnfparamvals *pvals;
	int i;
CODESTARTnewActInst
	DBGPRINTF("newActInst (mmutf8fix)\n");
	if((pvals = nvlstGetParams(lst, &actpblk, NULL)) == NULL) {
		ABORT_FINALIZE(RS_RET_MISSING_CNFPARAMS);
	}

	CODE_STD_STRING_REQUESTnewActInst(1)
	CHKiRet(OMSRsetEntry(*ppOMSR, 0, NULL, OMSR_TPL_AS_MSG));
	CHKiRet(createInstance(&pData));
	setInstParamDefaults(pData);

	for(i = 0 ; i < actpblk.nParams ; ++i) {
		if(!pvals[i].bUsed)
			continue;
		if(!strcmp(actpblk.descr[i].name, "mode")) {
			if(!es_strbufcmp(pvals[i].val.d.estr, (uchar*)"utf-8",
					 sizeof("utf-8")-1)) {
				pData->mode = MODE_UTF8;
			} else if(!es_strbufcmp(pvals[i].val.d.estr, (uchar*)"controlcharacters",
					 sizeof("controlcharacters")-1)) {
				pData->mode = MODE_CC;
			} else {
				char *cstr = es_str2cstr(pvals[i].val.d.estr, NULL);
				LogError(0, RS_RET_INVLD_MODE,
					"mmutf8fix: invalid mode '%s' - ignored",
					cstr);
				free(cstr);
			}
		} else if(!strcmp(actpblk.descr[i].name, "replacementchar")) {
			pData->replChar = es_getBufAddr(pvals[i].val.d.estr)[0];
		} else {
			dbgprintf("mmutf8fix: program error, non-handled "
			  "param '%s'\n", actpblk.descr[i].name);
		}
	}

CODE_STD_FINALIZERnewActInst
	cnfparamvalsDestruct(pvals, &actpblk);
ENDnewActInst


BEGINdbgPrintInstInfo
CODESTARTdbgPrintInstInfo
ENDdbgPrintInstInfo


BEGINtryResume
CODESTARTtryResume
ENDtryResume


static void
doCC(instanceData *pData, uchar *msg, int lenMsg)
{
	int i;

	for(i = 0 ; i < lenMsg ; ++i) {
		if(msg[i] < 32 || msg[i] > 126) {
			msg[i] = pData->replChar;
		}
	}
}

/* fix an invalid multibyte sequence */
static void
fixInvldMBSeq(instanceData *pData, uchar *msg, int lenMsg, int strtIdx, int cnt)
{
	int i, endIdx;

	/* Actually strtIdx + cnt will not exceed msgLen,
	   but this check does bring peace of mind */
	endIdx = strtIdx + cnt;
	if(endIdx > lenMsg)
		endIdx = lenMsg;
	for(i = strtIdx ; i < endIdx ; ++i)
		msg[i] = pData->replChar;
}

static void
doUTF8(instanceData *pData, uchar *msg, int lenMsg)
{
	uchar c;
	int8_t bytesLeft = 0;
	uint32_t codepoint;
	int strtIdx = 0;
	int i;

	for(i = 0 ; i < lenMsg ; ++i) {
		c = msg[i];
		if(bytesLeft) {
			if((c & 0xc0) != 0x80) {
				/* invalid continuation byte, invalidate all bytes
				   up to (but not including) the current byte
				   startIdx is always set if bytesLeft is set */
				fixInvldMBSeq(pData, msg, lenMsg, strtIdx, i - strtIdx);
				bytesLeft = 0;
				goto startOfSequence;
			} else {
				codepoint = (codepoint << 6) | (c & 0x3f);
				--bytesLeft;
				if(bytesLeft == 0) {
					int seqLen = i - strtIdx + 1;

					if (
					    /* an overlong encoding? (a codepoint must use only
					       the minimum number of bytes to represent its value) */
					    (((2 == seqLen) && (codepoint < 0x80)) ||
					     ((3 == seqLen) && (codepoint < 0x800)) ||
					     ((4 == seqLen) && (codepoint < 0x10000)))
					    ||
					    /* UTF-16 surrogates? */
					    ((codepoint >= 0xD800) && (codepoint <= 0xDFFF))
					    ||
					    /* too-large codepoint? */
					    (codepoint > 0x10FFFF)
					) {
						/* sequence invalid, invalidate all bytes
						   startIdx is always set if bytesLeft is set */
						fixInvldMBSeq(pData, msg, lenMsg, strtIdx, seqLen);
					}
				}
			}
		} else {
startOfSequence:
			if((c & 0x80) == 0) {
				/* 1-byte sequence, US-ASCII */
				; /* nothing to do, all well */
			} else if((c & 0xe0) == 0xc0) {
				/* 2-byte sequence */
				strtIdx = i;
				bytesLeft = 1;
				codepoint = c & 0x1f;
			} else if((c & 0xf0) == 0xe0) {
				/* 3-byte sequence */
				strtIdx = i;
				bytesLeft = 2;
				codepoint = c & 0x0f;
			} else if((c & 0xf8) == 0xf0) {
				/* 4-byte sequence */
				strtIdx = i;
				bytesLeft = 3;
				codepoint = c & 0x07;
			} else {   /* invalid, either:
				      - stray continuation byte (0x80 <= x <= 0xBF)
				      - 5&6 byte sequence start (x >= 0xF8) forbidden by RFC3629
				    */
				msg[i] = pData->replChar;
			}
		}
	}
	if (bytesLeft) {
		/* invalid, there was not enough bytes to complete a sequence
		   startIdx is always set if bytesLeft is set */
		fixInvldMBSeq(pData, msg, lenMsg, strtIdx, i - strtIdx);
	}
}

BEGINdoAction_NoStrings
	smsg_t **ppMsg = (smsg_t **) pMsgData;
	smsg_t *pMsg = ppMsg[0];
	uchar *msg;
	int lenMsg;
CODESTARTdoAction
	lenMsg = getMSGLen(pMsg);
	msg = getMSG(pMsg);
	if(pWrkrData->pData->mode == MODE_CC) {
		doCC(pWrkrData->pData, msg, lenMsg);
	} else {
		doUTF8(pWrkrData->pData, msg, lenMsg);
	}
ENDdoAction


NO_LEGACY_CONF_parseSelectorAct


BEGINmodExit
CODESTARTmodExit
ENDmodExit


BEGINqueryEtryPt
CODESTARTqueryEtryPt
CODEqueryEtryPt_STD_OMOD_QUERIES
CODEqueryEtryPt_STD_OMOD8_QUERIES
CODEqueryEtryPt_STD_CONF2_OMOD_QUERIES
CODEqueryEtryPt_STD_CONF2_QUERIES
ENDqueryEtryPt


BEGINmodInit()
CODESTARTmodInit
	*ipIFVersProvided = CURR_MOD_IF_VERSION; /* we only support the current interface specification */
CODEmodInit_QueryRegCFSLineHdlr
	DBGPRINTF("mmutf8fix: module compiled with rsyslog version %s.\n", VERSION);
ENDmodInit